Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1020 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.9650. Min Act: -0.1700
Data Index: 8603711 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8869. Min Act: -0.1700
Data Index: 5552761 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8400. Min Act: -0.1700
Data Index: 8691235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8400. Min Act: -0.1189
Data Index: 7624597 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8400. Min Act: -0.1700
Data Index: 1841708 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8400. Min Act: -0.1700
Data Index: 6466354 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8400. Min Act: -0.1700
Data Index: 2381318 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8087. Min Act: -0.1700
Data Index: 8097563 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8243. Min Act: -0.1676
Data Index: 6702693 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8243. Min Act: -0.1700
Data Index: 6246656 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8243. Min Act: -0.1700
Data Index: 5486781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8243. Min Act: -0.1700
Data Index: 8818948 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8087. Min Act: -0.1695
Data Index: 6259451 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8087. Min Act: -0.1700
Data Index: 6234874 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7774. Min Act: -0.1700
Data Index: 1632150 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7930. Min Act: -0.1700
Data Index: 8075376 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7930. Min Act: 0.0028
Data Index: 3070380 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7774. Min Act: -0.1700
Data Index: 1996596 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7774. Min Act: -0.1700
Data Index: 2987691 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7618. Min Act: -0.1700
Data Index: 6460571 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19