Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5418. Min Range: -7.5418
Max Act: 7.5418. Min Act: -0.1700
Data Index: 7970522 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5418. Min Range: -7.5418
Max Act: 7.4168. Min Act: -0.1700
Data Index: 8164806 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5418. Min Range: -7.5418
Max Act: 7.3543. Min Act: -0.1700
Data Index: 7115026 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5418. Min Range: -7.5418
Max Act: 7.2918. Min Act: -0.1700
Data Index: 7115019 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5418. Min Range: -7.5418
Max Act: 7.2293. Min Act: -0.1700
Data Index: 2310874 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.8856. Min Act: -0.1700
Data Index: 8184130 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.8856. Min Act: -0.1700
Data Index: 4439739 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.8231. Min Act: -0.1700
Data Index: 3227989 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.8231. Min Act: -0.1700
Data Index: 8330236 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.7918. Min Act: -0.1700
Data Index: 4333010 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.7918. Min Act: -0.1700
Data Index: 6928876 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.7606. Min Act: -0.1700
Data Index: 3076663 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.7606. Min Act: -0.1700
Data Index: 5118704 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 5705800 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 408204 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 3934670 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 2327645 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 4897778 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 2310858 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5418. Min Range: -7.5418
Max Act: 6.6043. Min Act: -0.1700
Data Index: 2893071 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19