Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3660. Min Range: -4.3660
Max Act: 4.3660. Min Act: -0.1700
Data Index: 3114625 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3660. Min Range: -4.3660
Max Act: 4.3347. Min Act: -0.1700
Data Index: 7920441 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3660. Min Range: -4.3660
Max Act: 4.0534. Min Act: -0.1700
Data Index: 4281634 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3660. Min Range: -4.3660
Max Act: 4.0222. Min Act: -0.1700
Data Index: 5069904 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9596. Min Act: -0.1700
Data Index: 4360830 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9596. Min Act: -0.1700
Data Index: 2434386 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 6252630 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 3775304 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 1397388 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 8473220 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 7952400 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 3318213 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9284. Min Act: -0.1700
Data Index: 4664641 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.8971. Min Act: -0.1700
Data Index: 4226149 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.9596. Min Act: -0.1700
Data Index: 3750558 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.8346. Min Act: -0.1700
Data Index: 1764187 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.8658. Min Act: -0.1700
Data Index: 7834930 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.8658. Min Act: -0.1700
Data Index: 4421963 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.8658. Min Act: -0.1700
Data Index: 3428921 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3660. Min Range: -4.3660
Max Act: 3.8658. Min Act: -0.1700
Data Index: 4233577 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19