Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1059 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.9935. Min Act: -0.1700
Data Index: 422992 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.7435. Min Act: -0.1700
Data Index: 1862954 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.7122. Min Act: -0.1700
Data Index: 2105847 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.7435. Min Act: -0.1700
Data Index: 8380762 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.6810. Min Act: -0.1700
Data Index: 3336012 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.6810. Min Act: -0.1700
Data Index: 5795296 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.6497. Min Act: -0.1700
Data Index: 529818 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.5872. Min Act: -0.1700
Data Index: 2411544 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.5872. Min Act: -0.1700
Data Index: 2344262 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.4935. Min Act: -0.1700
Data Index: 6657048 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.4622. Min Act: -0.1700
Data Index: 3419456 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3997. Min Act: -0.1700
Data Index: 5723955 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3997. Min Act: -0.1700
Data Index: 1711128 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3997. Min Act: -0.1700
Data Index: 7542216 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3685. Min Act: -0.1700
Data Index: 7731212 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3685. Min Act: -0.1700
Data Index: 2624095 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3060. Min Act: -0.1700
Data Index: 3701400 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3060. Min Act: -0.1700
Data Index: 5749755 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.2747. Min Act: -0.1700
Data Index: 7745712 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9935. Min Range: -6.9935
Max Act: 6.3372. Min Act: -0.1700
Data Index: 4029363 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19