Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1825. Min Range: -7.1825
Max Act: 7.1825. Min Act: -0.1700
Data Index: 1005230 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1825. Min Range: -7.1825
Max Act: 7.0888. Min Act: -0.1700
Data Index: 7779266 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1825. Min Range: -7.1825
Max Act: 7.0263. Min Act: -0.1700
Data Index: 4234399 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.9638. Min Act: -0.1700
Data Index: 7560731 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.9638. Min Act: -0.1700
Data Index: 7536273 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.9325. Min Act: -0.1700
Data Index: 1213091 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.9013. Min Act: -0.1700
Data Index: 1283922 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.8700. Min Act: -0.1700
Data Index: 1050317 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.8388. Min Act: -0.1700
Data Index: 8402264 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.8075. Min Act: -0.1700
Data Index: 8588229 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.8388. Min Act: -0.1700
Data Index: 8001604 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7763. Min Act: -0.1700
Data Index: 1064127 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7450. Min Act: -0.1700
Data Index: 5060005 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7450. Min Act: -0.1700
Data Index: 4851897 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7450. Min Act: -0.1700
Data Index: 8340373 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7450. Min Act: -0.1700
Data Index: 1651027 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7450. Min Act: -0.1700
Data Index: 8057485 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7450. Min Act: -0.1700
Data Index: 4978341 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7138. Min Act: -0.1700
Data Index: 974137 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1825. Min Range: -7.1825
Max Act: 6.7138. Min Act: -0.1700
Data Index: 7534375 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19