Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5861 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1969. Min Range: -5.1969
Max Act: 5.1969. Min Act: -0.1700
Data Index: 7968048 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1969. Min Range: -5.1969
Max Act: 5.0407. Min Act: -0.1700
Data Index: 3365843 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1969. Min Range: -5.1969
Max Act: 5.0407. Min Act: -0.1700
Data Index: 8327354 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.9469. Min Act: -0.1700
Data Index: 531293 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.9157. Min Act: -0.1700
Data Index: 269663 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8844. Min Act: -0.1700
Data Index: 8535360 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8844. Min Act: -0.1700
Data Index: 1243034 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.9157. Min Act: -0.1700
Data Index: 3589091 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8844. Min Act: -0.1700
Data Index: 8480468 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8844. Min Act: -0.1700
Data Index: 2827443 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8844. Min Act: -0.1700
Data Index: 1803635 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8532. Min Act: -0.1700
Data Index: 1383101 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8532. Min Act: -0.1700
Data Index: 7046778 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8532. Min Act: -0.1700
Data Index: 1526414 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8219. Min Act: -0.1700
Data Index: 2463052 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8532. Min Act: -0.1700
Data Index: 2396796 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8219. Min Act: -0.1700
Data Index: 6306186 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8219. Min Act: -0.1700
Data Index: 8065254 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.8219. Min Act: -0.1700
Data Index: 1766667 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1969. Min Range: -5.1969
Max Act: 4.7907. Min Act: -0.1700
Data Index: 3167641 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19