Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5379 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.5053. Min Act: -0.1700
Data Index: 6280394 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.4740. Min Act: -0.1700
Data Index: 1787717 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 2030203 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 4933464 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2240. Min Act: -0.1700
Data Index: 7646102 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1615. Min Act: -0.1700
Data Index: 7206941 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1615. Min Act: -0.1700
Data Index: 1266196 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0990. Min Act: -0.1700
Data Index: 4891200 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.1303. Min Act: -0.1700
Data Index: 7564565 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8685894 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0365. Min Act: -0.1700
Data Index: 5483576 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0365. Min Act: -0.1700
Data Index: 3185278 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0053. Min Act: -0.1700
Data Index: 7628253 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0053. Min Act: -0.1700
Data Index: 7763370 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0053. Min Act: -0.1700
Data Index: 1327552 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0053. Min Act: -0.1700
Data Index: 3559701 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.0053. Min Act: -0.1700
Data Index: 6700341 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5053. Min Range: -5.5053
Max Act: 4.9740. Min Act: -0.1700
Data Index: 1091594 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5053. Min Range: -5.5053
Max Act: 4.9740. Min Act: -0.1700
Data Index: 1026244 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5053. Min Range: -5.5053
Max Act: 4.9428. Min Act: -0.1700
Data Index: 2816564 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19