Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4567 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0471. Min Range: -10.0471
Max Act: 10.0471. Min Act: -0.1700
Data Index: 4454168 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.5471. Min Act: -0.1700
Data Index: 7075582 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.5471. Min Act: -0.1700
Data Index: 2384180 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.4846. Min Act: -0.1700
Data Index: 3777967 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.4221. Min Act: -0.1700
Data Index: 4286236 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.2971. Min Act: -0.1700
Data Index: 5357240 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.2346. Min Act: -0.1700
Data Index: 1297156 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.2346. Min Act: -0.1700
Data Index: 2762726 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.1721. Min Act: -0.1700
Data Index: 4454530 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.1096. Min Act: -0.1700
Data Index: 8164160 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0471. Min Range: -10.0471
Max Act: 9.0471. Min Act: -0.1700
Data Index: 3728096 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9221. Min Act: -0.1700
Data Index: 6114073 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9846. Min Act: -0.1700
Data Index: 5611351 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9846. Min Act: -0.1700
Data Index: 7580032 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9846. Min Act: -0.1700
Data Index: 7253139 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9846. Min Act: -0.1700
Data Index: 6808827 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9846. Min Act: -0.1700
Data Index: 6363150 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9221. Min Act: -0.1700
Data Index: 7540909 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9221. Min Act: -0.1700
Data Index: 2793885 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0471. Min Range: -10.0471
Max Act: 8.9846. Min Act: -0.1700
Data Index: 187563 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19