Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1123. Min Range: -5.1123
Max Act: 5.1123. Min Act: -0.1700
Data Index: 1003884 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1123. Min Range: -5.1123
Max Act: 5.0810. Min Act: -0.1700
Data Index: 3090534 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1123. Min Range: -5.1123
Max Act: 5.0498. Min Act: -0.1700
Data Index: 6521922 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1123. Min Range: -5.1123
Max Act: 5.0185. Min Act: -0.1700
Data Index: 7075357 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.8310. Min Act: -0.1700
Data Index: 4832307 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.7998. Min Act: -0.1700
Data Index: 5124597 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.7685. Min Act: -0.1700
Data Index: 2178128 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.7373. Min Act: -0.1700
Data Index: 1384943 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.7060. Min Act: -0.1700
Data Index: 4090933 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.7060. Min Act: -0.1700
Data Index: 1985181 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.6748. Min Act: -0.1700
Data Index: 5341749 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.7060. Min Act: -0.1700
Data Index: 8783202 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.6748. Min Act: -0.1700
Data Index: 4287850 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.6748. Min Act: -0.1700
Data Index: 7744158 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.6435. Min Act: -0.1700
Data Index: 6756564 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.6435. Min Act: -0.1700
Data Index: 5712932 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.6123. Min Act: -0.1700
Data Index: 4815567 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.5810. Min Act: -0.1700
Data Index: 4776237 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.5810. Min Act: -0.1700
Data Index: 445246 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1123. Min Range: -5.1123
Max Act: 4.5810. Min Act: -0.1700
Data Index: 1571694 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19