Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.3598. Min Act: -0.1700
Data Index: 2176560 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.3598. Min Act: -0.1700
Data Index: 5584286 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.3286. Min Act: -0.1700
Data Index: 466716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2661. Min Act: -0.1699
Data Index: 856959 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2348. Min Act: -0.1700
Data Index: 1294430 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1700
Data Index: 3688241 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1699
Data Index: 227816 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1700
Data Index: 5258134 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1700
Data Index: 8655979 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1700
Data Index: 2750169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1700
Data Index: 8677161 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.2036. Min Act: -0.1700
Data Index: 4421142 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2427427 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2925458 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2575709 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1411. Min Act: -0.1700
Data Index: 2011898 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1411. Min Act: -0.1700
Data Index: 6625783 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1411. Min Act: -0.1700
Data Index: 6923778 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1411. Min Act: -0.1700
Data Index: 6748625 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3598. Min Range: -5.3598
Max Act: 5.1098. Min Act: -0.1700
Data Index: 1327 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19