Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4684. Min Range: -7.4684
Max Act: 7.4684. Min Act: -0.1700
Data Index: 2890059 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4684. Min Range: -7.4684
Max Act: 7.0309. Min Act: -0.1700
Data Index: 4010834 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.9371. Min Act: -0.1700
Data Index: 5349156 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.9371. Min Act: -0.1700
Data Index: 8579560 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.8746. Min Act: -0.1700
Data Index: 485365 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.8434. Min Act: -0.1700
Data Index: 7344014 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.7809. Min Act: -0.1700
Data Index: 2805335 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6871. Min Act: -0.1700
Data Index: 4796921 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6871. Min Act: -0.1700
Data Index: 931324 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6559. Min Act: -0.1700
Data Index: 8274057 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6559. Min Act: -0.1700
Data Index: 7345388 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6559. Min Act: -0.1700
Data Index: 6757608 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6559. Min Act: -0.1700
Data Index: 6019149 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6559. Min Act: -0.1700
Data Index: 2243566 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6246. Min Act: -0.1700
Data Index: 3742566 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6246. Min Act: -0.1700
Data Index: 1724234 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6246. Min Act: -0.1700
Data Index: 8508232 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.5934. Min Act: -0.1700
Data Index: 2805336 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.5934. Min Act: -0.1700
Data Index: 4761135 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4684. Min Range: -7.4684
Max Act: 6.6246. Min Act: -0.1700
Data Index: 128908 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19