Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.8118. Min Act: -0.1700
Data Index: 6684641 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.6868. Min Act: -0.1700
Data Index: 6425999 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.5618. Min Act: -0.1700
Data Index: 2435191 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.5306. Min Act: -0.1700
Data Index: 1489537 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.4993. Min Act: -0.1700
Data Index: 8058630 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.4056. Min Act: -0.1700
Data Index: 3921723 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.3118. Min Act: -0.1700
Data Index: 781380 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.3118. Min Act: -0.1700
Data Index: 8135340 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.2493. Min Act: -0.1700
Data Index: 4939941 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.2181. Min Act: -0.1700
Data Index: 5376203 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1868. Min Act: -0.1700
Data Index: 1947454 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.2181. Min Act: -0.1700
Data Index: 6496343 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1868. Min Act: -0.1700
Data Index: 4350295 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1868. Min Act: -0.1700
Data Index: 2674246 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1556. Min Act: -0.1700
Data Index: 7396962 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1556. Min Act: -0.1700
Data Index: 5052003 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1868. Min Act: -0.1700
Data Index: 408285 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1556. Min Act: -0.1700
Data Index: 2377457 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1243. Min Act: -0.1700
Data Index: 3891110 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8118. Min Range: -7.8118
Max Act: 7.1243. Min Act: -0.1700
Data Index: 1367935 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19