Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 840 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.1159. Min Act: -0.1700
Data Index: 8759564 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.0686. Min Act: -0.1700
Data Index: 4730208 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.0370. Min Act: -0.1700
Data Index: 2351498 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.0528. Min Act: -0.1700
Data Index: 6917109 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.0370. Min Act: -0.1700
Data Index: 6592181 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.0055. Min Act: -0.1700
Data Index: 4668532 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1159. Min Range: -3.1159
Max Act: 3.0055. Min Act: -0.1700
Data Index: 5269994 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9896. Min Act: -0.1700
Data Index: 3818800 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9580. Min Act: -0.1700
Data Index: 5375039 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9422. Min Act: -0.1700
Data Index: 7298955 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9580. Min Act: -0.1700
Data Index: 7172980 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9422. Min Act: -0.1700
Data Index: 980560 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9263. Min Act: -0.1700
Data Index: 7758090 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9263. Min Act: -0.1700
Data Index: 4885592 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9105. Min Act: -0.1700
Data Index: 732577 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9105. Min Act: -0.1700
Data Index: 4557897 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9105. Min Act: -0.1700
Data Index: 1092671 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.9105. Min Act: -0.1700
Data Index: 2172132 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.8946. Min Act: -0.1700
Data Index: 333625 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1159. Min Range: -3.1159
Max Act: 2.8946. Min Act: -0.1700
Data Index: 7205407 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19