Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1202 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4864. Min Range: -8.4864
Max Act: 8.4864. Min Act: -0.1700
Data Index: 7674386 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4864. Min Range: -8.4864
Max Act: 8.1114. Min Act: -0.1700
Data Index: 3974854 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4864. Min Range: -8.4864
Max Act: 8.0489. Min Act: -0.1700
Data Index: 334594 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.7364. Min Act: -0.1700
Data Index: 7193310 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.6739. Min Act: -0.1700
Data Index: 296538 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.5489. Min Act: -0.1700
Data Index: 1140415 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.5489. Min Act: -0.1700
Data Index: 5650879 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.4864. Min Act: -0.1700
Data Index: 424091 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.4239. Min Act: -0.1700
Data Index: 8787205 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.4239. Min Act: -0.1700
Data Index: 2266532 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3926. Min Act: -0.1700
Data Index: 7617795 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3926. Min Act: -0.1700
Data Index: 97790 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3614. Min Act: -0.1700
Data Index: 3226086 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3614. Min Act: -0.1700
Data Index: 5725410 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3614. Min Act: -0.1700
Data Index: 6367038 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3301. Min Act: -0.1700
Data Index: 3371803 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.3301. Min Act: -0.1700
Data Index: 6256040 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.2989. Min Act: -0.1700
Data Index: 2741025 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.2364. Min Act: -0.1700
Data Index: 1436312 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4864. Min Range: -8.4864
Max Act: 7.2364. Min Act: -0.1700
Data Index: 6236255 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19