Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1944. Min Act: -0.1700
Data Index: 1528368 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1944. Min Act: -0.1700
Data Index: 680597 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1631. Min Act: -0.1700
Data Index: 8832193 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1631. Min Act: -0.1700
Data Index: 536736 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1631. Min Act: -0.1700
Data Index: 680598 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1631. Min Act: -0.1700
Data Index: 2462200 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 7284309 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 7529081 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 7012466 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 6690326 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 2558041 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 5782350 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 1370960 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 2166508 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 8832192 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1318. Min Act: -0.1700
Data Index: 492725 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1006. Min Act: -0.1700
Data Index: 6672145 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1006. Min Act: -0.1700
Data Index: 2419348 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.1006. Min Act: -0.1700
Data Index: 2795098 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1944. Min Range: -4.1944
Max Act: 4.0693. Min Act: -0.1700
Data Index: 7225333 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19