Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.9337. Min Act: -0.1700
Data Index: 8548871 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8861. Min Act: -0.1700
Data Index: 7449831 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8861. Min Act: -0.1700
Data Index: 526265 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8544. Min Act: -0.1700
Data Index: 4151156 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8226. Min Act: -0.1700
Data Index: 5581919 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8385. Min Act: -0.1700
Data Index: 3187492 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8385. Min Act: -0.1700
Data Index: 7437613 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8226. Min Act: -0.1700
Data Index: 6784283 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8226. Min Act: -0.1700
Data Index: 3734320 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.8226. Min Act: -0.1700
Data Index: 6104248 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7908. Min Act: -0.1700
Data Index: 8633470 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7748. Min Act: -0.1700
Data Index: 938223 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7748. Min Act: -0.1700
Data Index: 4702000 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7589. Min Act: -0.1700
Data Index: 2555511 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7589. Min Act: -0.1700
Data Index: 5469953 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7589. Min Act: -0.1700
Data Index: 6070558 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7429. Min Act: -0.1700
Data Index: 4161434 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7589. Min Act: -0.1700
Data Index: 54949 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7429. Min Act: -0.1700
Data Index: 4783288 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9337. Min Range: -2.9337
Max Act: 2.7269. Min Act: -0.1700
Data Index: 4192726 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19