Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2035 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3193. Min Range: -6.3193
Max Act: 6.3193. Min Act: -0.1700
Data Index: 6038733 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3193. Min Range: -6.3193
Max Act: 6.3193. Min Act: -0.1700
Data Index: 307131 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7809852 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.9443. Min Act: -0.1700
Data Index: 6478989 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8818. Min Act: -0.1700
Data Index: 98625 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8818. Min Act: -0.1700
Data Index: 3854873 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8506. Min Act: -0.1700
Data Index: 3317735 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8506. Min Act: -0.1700
Data Index: 6151927 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8506. Min Act: -0.1700
Data Index: 4039893 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 5272486 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 6764639 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8193. Min Act: -0.1700
Data Index: 247454 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.8193. Min Act: -0.1700
Data Index: 4035544 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 4120392 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 3592122 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 8031100 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 3046431 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 6478990 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 3476214 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3193. Min Range: -6.3193
Max Act: 5.7881. Min Act: -0.1700
Data Index: 736997 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19