Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.6971. Min Act: -0.1700
Data Index: 3714419 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5406. Min Act: -0.1696
Data Index: 1467078 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.5406. Min Act: -0.1700
Data Index: 7129555 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4779. Min Act: -0.1700
Data Index: 2960094 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4779. Min Act: -0.1700
Data Index: 8758204 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4466. Min Act: -0.1700
Data Index: 8368383 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4152. Min Act: -0.1700
Data Index: 5100750 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4152. Min Act: -0.1699
Data Index: 834167 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4152. Min Act: -0.1700
Data Index: 8381976 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.4152. Min Act: -0.1700
Data Index: 4472649 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.3839. Min Act: -0.1700
Data Index: 6978218 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.3211. Min Act: -0.1699
Data Index: 6501744 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.3211. Min Act: -0.1698
Data Index: 8295956 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.3211. Min Act: -0.1700
Data Index: 6543740 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.3054. Min Act: -0.1699
Data Index: 6169613 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.3211. Min Act: -0.1699
Data Index: 1886111 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.2897. Min Act: -0.1698
Data Index: 293290 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.2583. Min Act: -0.1700
Data Index: 6456513 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.2583. Min Act: -0.1691
Data Index: 4883879 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6971. Min Range: -3.6971
Max Act: 3.2269. Min Act: -0.1700
Data Index: 7645351 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19