Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.9443. Min Act: -0.1700
Data Index: 8533846 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.9130. Min Act: -0.1700
Data Index: 4443467 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.8818. Min Act: -0.1700
Data Index: 7923637 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.8818. Min Act: -0.1700
Data Index: 8271757 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.8505. Min Act: -0.1700
Data Index: 6509832 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.8193. Min Act: -0.1700
Data Index: 5382205 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7880. Min Act: -0.1700
Data Index: 8689430 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7880. Min Act: -0.1700
Data Index: 749211 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7880. Min Act: -0.1700
Data Index: 1074609 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7880. Min Act: -0.1700
Data Index: 3234429 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7567. Min Act: -0.1700
Data Index: 4963877 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7255. Min Act: -0.1700
Data Index: 4003651 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.7255. Min Act: -0.1700
Data Index: 7210544 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.6630. Min Act: -0.1700
Data Index: 6189959 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.6630. Min Act: -0.1700
Data Index: 2835070 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.6630. Min Act: -0.1700
Data Index: 4963876 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.6317. Min Act: -0.1700
Data Index: 7092559 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.5692. Min Act: -0.1700
Data Index: 3396819 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.6005. Min Act: -0.1700
Data Index: 2174326 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9443. Min Range: -4.9443
Max Act: 4.6005. Min Act: -0.1700
Data Index: 4987642 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19