Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2406 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4214. Min Range: -9.4214
Max Act: 9.4214. Min Act: -0.1700
Data Index: 1871931 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4214. Min Range: -9.4214
Max Act: 9.1089. Min Act: -0.1697
Data Index: 537681 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.9214. Min Act: -0.1700
Data Index: 4986952 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.7964. Min Act: -0.1700
Data Index: 7611748 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.5464. Min Act: -0.1699
Data Index: 3168721 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.4839. Min Act: -0.1700
Data Index: 6448978 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.4214. Min Act: -0.1697
Data Index: 841579 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.2964. Min Act: -0.1699
Data Index: 5667643 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.2964. Min Act: -0.1699
Data Index: 5514788 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.2339. Min Act: -0.1700
Data Index: 2189900 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.2964. Min Act: -0.1700
Data Index: 5596603 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.2964. Min Act: -0.1700
Data Index: 1908602 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.2026. Min Act: -0.1700
Data Index: 3370933 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.1089. Min Act: -0.1700
Data Index: 1092982 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.1401. Min Act: -0.1700
Data Index: 3243096 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.0464. Min Act: -0.1700
Data Index: 3943568 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4214. Min Range: -9.4214
Max Act: 8.0151. Min Act: -0.1700
Data Index: 7517540 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4214. Min Range: -9.4214
Max Act: 7.9839. Min Act: -0.1680
Data Index: 1543541 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4214. Min Range: -9.4214
Max Act: 7.9214. Min Act: -0.1697
Data Index: 4561100 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4214. Min Range: -9.4214
Max Act: 7.9839. Min Act: -0.1687
Data Index: 6188180 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19