Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1245 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4347. Min Range: -11.4347
Max Act: 11.4347. Min Act: -0.1700
Data Index: 2879017 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4347. Min Range: -11.4347
Max Act: 11.3097. Min Act: -0.1700
Data Index: 23319 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4347. Min Range: -11.4347
Max Act: 10.9347. Min Act: -0.1700
Data Index: 3776186 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4347. Min Range: -11.4347
Max Act: 10.6222. Min Act: -0.1700
Data Index: 6617578 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4347. Min Range: -11.4347
Max Act: 10.4972. Min Act: -0.1700
Data Index: 4980023 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4347. Min Range: -11.4347
Max Act: 10.2472. Min Act: -0.1700
Data Index: 7876601 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4347. Min Range: -11.4347
Max Act: 10.1222. Min Act: -0.1700
Data Index: 1869558 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4347. Min Range: -11.4347
Max Act: 10.0597. Min Act: -0.1700
Data Index: 2640148 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.9972. Min Act: -0.1700
Data Index: 55740 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.8722. Min Act: -0.1700
Data Index: 7763164 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.8722. Min Act: -0.1700
Data Index: 4619618 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.8722. Min Act: -0.1700
Data Index: 7498996 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.8097. Min Act: -0.1700
Data Index: 5942896 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.7472. Min Act: -0.1700
Data Index: 7510037 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.7472. Min Act: -0.1700
Data Index: 6555082 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.7472. Min Act: -0.1700
Data Index: 1187944 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.6847. Min Act: -0.1700
Data Index: 4230170 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.6847. Min Act: -0.1700
Data Index: 6915415 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.6847. Min Act: -0.1700
Data Index: 3900029 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4347. Min Range: -11.4347
Max Act: 9.6847. Min Act: -0.1700
Data Index: 3327802 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19