Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.4675. Min Range: -11.4675
Max Act: 11.4675. Min Act: -0.1700
Data Index: 6246761 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.8425. Min Act: -0.1700
Data Index: 3375134 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.7175. Min Act: -0.1700
Data Index: 3380511 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.5925. Min Act: -0.1700
Data Index: 2082949 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.5925. Min Act: -0.1700
Data Index: 3408604 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.4675. Min Act: -0.1700
Data Index: 3443878 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.4675. Min Act: -0.1700
Data Index: 78066 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.4675. Min Act: -0.1700
Data Index: 8241906 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.4050. Min Act: -0.1700
Data Index: 1177298 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.3425. Min Act: -0.1700
Data Index: 121361 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.3425. Min Act: -0.1700
Data Index: 1550705 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.3425. Min Act: -0.1700
Data Index: 599780 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.3425. Min Act: -0.1700
Data Index: 6457074 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.3425. Min Act: -0.1700
Data Index: 1621971 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.2800. Min Act: -0.1700
Data Index: 8737540 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.1550. Min Act: -0.1700
Data Index: 4138665 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.2175. Min Act: -0.1700
Data Index: 256652 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.2175. Min Act: -0.1700
Data Index: 7422878 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.1550. Min Act: -0.1700
Data Index: 3501835 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4675. Min Range: -11.4675
Max Act: 10.2175. Min Act: -0.1700
Data Index: 720553 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19