Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.7284. Min Act: -0.1700
Data Index: 1040949 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.7284. Min Act: -0.1700
Data Index: 7899150 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.6971. Min Act: -0.1700
Data Index: 8131718 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.6346. Min Act: -0.1700
Data Index: 4355846 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.6346. Min Act: -0.1700
Data Index: 212522 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.6346. Min Act: -0.1700
Data Index: 1475166 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.6034. Min Act: -0.1700
Data Index: 3402759 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.5721. Min Act: -0.1700
Data Index: 6532597 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.5721. Min Act: -0.1700
Data Index: 8131722 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.5409. Min Act: -0.1700
Data Index: 1418643 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4784. Min Act: -0.1700
Data Index: 6847225 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4784. Min Act: -0.1700
Data Index: 4221903 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4159. Min Act: -0.1700
Data Index: 3402764 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4471. Min Act: -0.1700
Data Index: 1317561 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4784. Min Act: -0.1700
Data Index: 858275 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4471. Min Act: -0.1700
Data Index: 3819005 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4471. Min Act: -0.1700
Data Index: 4281089 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4159. Min Act: -0.1700
Data Index: 6196835 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4159. Min Act: -0.1700
Data Index: 6532599 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7284. Min Range: -5.7284
Max Act: 5.4159. Min Act: -0.1700
Data Index: 1007558 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19