Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4589 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1983. Min Range: -6.1983
Max Act: 6.1983. Min Act: -0.1700
Data Index: 5654594 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1983. Min Range: -6.1983
Max Act: 6.1671. Min Act: -0.1700
Data Index: 5351288 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.9796. Min Act: -0.1700
Data Index: 7180931 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.9483. Min Act: -0.1700
Data Index: 4838303 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.8858. Min Act: -0.1700
Data Index: 4838299 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.8546. Min Act: -0.1700
Data Index: 4572655 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.8233. Min Act: -0.1700
Data Index: 12186 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.8546. Min Act: -0.1700
Data Index: 8239683 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.7608. Min Act: -0.1700
Data Index: 4838304 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.7296. Min Act: -0.1700
Data Index: 1981986 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6671. Min Act: -0.1700
Data Index: 4291166 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 251814 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6358. Min Act: -0.1700
Data Index: 7180936 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6671. Min Act: -0.1700
Data Index: 1195567 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 3688593 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6358. Min Act: -0.1700
Data Index: 2544641 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6358. Min Act: -0.1700
Data Index: 3820333 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6358. Min Act: -0.1700
Data Index: 7136736 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.6046. Min Act: -0.1700
Data Index: 1981992 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1983. Min Range: -6.1983
Max Act: 5.5733. Min Act: -0.1700
Data Index: 8137097 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19