Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3422. Min Range: -7.3422
Max Act: 7.3422. Min Act: -0.1700
Data Index: 1381360 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.9047. Min Act: -0.1700
Data Index: 8189957 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.7797. Min Act: -0.1700
Data Index: 5780800 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.6859. Min Act: -0.1700
Data Index: 3107251 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.6234. Min Act: -0.1700
Data Index: 5446642 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.5609. Min Act: -0.1700
Data Index: 1276011 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.5297. Min Act: -0.1700
Data Index: 4122598 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4984. Min Act: -0.1700
Data Index: 7302246 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4984. Min Act: -0.1700
Data Index: 4611163 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4984. Min Act: -0.1700
Data Index: 5330734 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4984. Min Act: -0.1700
Data Index: 5396203 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4984. Min Act: -0.1700
Data Index: 128377 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4672. Min Act: -0.1700
Data Index: 1053571 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4672. Min Act: -0.1700
Data Index: 5647292 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4359. Min Act: -0.1700
Data Index: 3520063 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4047. Min Act: -0.1700
Data Index: 3848215 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.4047. Min Act: -0.1700
Data Index: 4218941 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.3422. Min Act: -0.1700
Data Index: 497663 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.3422. Min Act: -0.1700
Data Index: 3841841 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3422. Min Range: -7.3422
Max Act: 6.3734. Min Act: -0.1700
Data Index: 4122428 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19