Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.7116. Min Act: -0.1700
Data Index: 4630908 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.6491. Min Act: -0.1700
Data Index: 2261045 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.6491. Min Act: -0.1700
Data Index: 4528188 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.6179. Min Act: -0.1700
Data Index: 3696402 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5866. Min Act: -0.1700
Data Index: 1615942 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5866. Min Act: -0.1700
Data Index: 7604945 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 5257299 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5554. Min Act: -0.1700
Data Index: 1364080 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 712735 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5554. Min Act: -0.1700
Data Index: 7734209 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 5376545 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 3081302 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 1275805 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.5241. Min Act: -0.1700
Data Index: 4805274 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4929. Min Act: -0.1700
Data Index: 5804571 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4929. Min Act: -0.1700
Data Index: 1648588 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4929. Min Act: -0.1700
Data Index: 6370958 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4929. Min Act: -0.1700
Data Index: 6487784 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4929. Min Act: -0.1700
Data Index: 4574158 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7116. Min Range: -5.7116
Max Act: 5.4929. Min Act: -0.1700
Data Index: 4390200 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19