Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.4149. Min Act: -0.1700
Data Index: 407646 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.3837. Min Act: -0.1700
Data Index: 990250 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.3524. Min Act: -0.1700
Data Index: 3269748 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.3212. Min Act: -0.1700
Data Index: 2666251 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.3212. Min Act: -0.1700
Data Index: 4994242 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2899. Min Act: -0.1700
Data Index: 2238271 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2899. Min Act: -0.1700
Data Index: 2029489 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2274. Min Act: -0.1700
Data Index: 4852733 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2587. Min Act: -0.1700
Data Index: 424456 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2587. Min Act: -0.1700
Data Index: 3513982 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2587. Min Act: -0.1700
Data Index: 87702 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2274. Min Act: -0.1700
Data Index: 3434754 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2274. Min Act: -0.1700
Data Index: 6520958 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2274. Min Act: -0.1700
Data Index: 8229169 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2274. Min Act: -0.1700
Data Index: 5892284 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.2274. Min Act: -0.1700
Data Index: 853207 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3092468 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.1962. Min Act: -0.1700
Data Index: 681824 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.1962. Min Act: -0.1700
Data Index: 5357782 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4149. Min Range: -5.4149
Max Act: 5.1649. Min Act: -0.1700
Data Index: 5527949 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19