Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4272. Min Range: -8.4272
Max Act: 8.4272. Min Act: -0.1700
Data Index: 5757218 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.4272. Min Act: -0.1700
Data Index: 54077 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.4272. Min Act: -0.1700
Data Index: 5942953 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.3334. Min Act: -0.1700
Data Index: 3385666 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.3022. Min Act: -0.1700
Data Index: 8544740 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.3334. Min Act: -0.1700
Data Index: 4547459 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.2397. Min Act: -0.1700
Data Index: 4617708 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.2397. Min Act: -0.1700
Data Index: 6175499 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.2084. Min Act: -0.1700
Data Index: 5621090 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.1459. Min Act: -0.1700
Data Index: 4207524 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.1459. Min Act: -0.1700
Data Index: 7492737 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.0834. Min Act: -0.1700
Data Index: 7409152 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.1147. Min Act: -0.1700
Data Index: 2964101 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.1459. Min Act: -0.1700
Data Index: 5652687 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.1147. Min Act: -0.1700
Data Index: 6020038 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.0834. Min Act: -0.1700
Data Index: 139520 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.0834. Min Act: -0.1700
Data Index: 1314974 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.0522. Min Act: -0.1700
Data Index: 8029391 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.0522. Min Act: -0.1700
Data Index: 3796230 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.0522. Min Act: -0.1700
Data Index: 142592 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19