Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8548353 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.6466. Min Act: -0.1700
Data Index: 4517506 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5529. Min Act: -0.1700
Data Index: 4619238 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.5216. Min Act: -0.1700
Data Index: 520689 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4279. Min Act: -0.1700
Data Index: 5803823 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4279. Min Act: -0.1700
Data Index: 6138781 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.4279. Min Act: -0.1700
Data Index: 8605602 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3966. Min Act: -0.1700
Data Index: 3883960 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3966. Min Act: -0.1700
Data Index: 5938123 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3966. Min Act: -0.1700
Data Index: 5254454 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3654. Min Act: -0.1700
Data Index: 8643647 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3654. Min Act: -0.1700
Data Index: 2886468 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3654. Min Act: -0.1700
Data Index: 2103972 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3654. Min Act: -0.1700
Data Index: 6460264 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3966. Min Act: -0.1700
Data Index: 4990580 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3341. Min Act: -0.1700
Data Index: 5737704 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3341. Min Act: -0.1700
Data Index: 67687 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3341. Min Act: -0.1700
Data Index: 1355525 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3341. Min Act: -0.1700
Data Index: 171687 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7091. Min Range: -5.7091
Max Act: 5.3341. Min Act: -0.1700
Data Index: 6683641 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19