Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.8804. Min Act: -0.1700
Data Index: 5176631 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.7866. Min Act: -0.1700
Data Index: 5587211 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.7554. Min Act: -0.1700
Data Index: 4164898 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.6929. Min Act: -0.1700
Data Index: 7821856 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.7241. Min Act: -0.1700
Data Index: 8038223 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.7241. Min Act: -0.1700
Data Index: 943120 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.6929. Min Act: -0.1700
Data Index: 7233931 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5366. Min Act: -0.1700
Data Index: 6532173 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5991. Min Act: -0.1700
Data Index: 3263175 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5679. Min Act: -0.1700
Data Index: 7373066 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5366. Min Act: -0.1700
Data Index: 8263257 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5366. Min Act: -0.1700
Data Index: 7639213 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5366. Min Act: -0.1700
Data Index: 3338784 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5366. Min Act: -0.1700
Data Index: 974287 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5054. Min Act: -0.1700
Data Index: 5061927 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.5366. Min Act: -0.1700
Data Index: 5015601 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.4741. Min Act: -0.1700
Data Index: 721829 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.4741. Min Act: -0.1700
Data Index: 4850603 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.4116. Min Act: -0.1700
Data Index: 2674652 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8804. Min Range: -6.8804
Max Act: 6.4429. Min Act: -0.1700
Data Index: 3016548 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19