Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.6812. Min Act: -0.1700
Data Index: 5275610 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.6812. Min Act: -0.1700
Data Index: 1286212 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.5562. Min Act: -0.1700
Data Index: 6203474 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.5250. Min Act: -0.1700
Data Index: 2412235 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.4312. Min Act: -0.1700
Data Index: 835484 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.4312. Min Act: -0.1700
Data Index: 5922079 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3687. Min Act: -0.1700
Data Index: 1491104 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.4000. Min Act: -0.1700
Data Index: 6877731 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.4000. Min Act: -0.1700
Data Index: 7991146 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3687. Min Act: -0.1700
Data Index: 7449180 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3687. Min Act: -0.1700
Data Index: 28226 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3687. Min Act: -0.1700
Data Index: 1937030 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3375. Min Act: -0.1700
Data Index: 1999702 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3062. Min Act: -0.1700
Data Index: 5619713 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.3062. Min Act: -0.1700
Data Index: 1706194 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.2750. Min Act: -0.1700
Data Index: 5410688 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.2750. Min Act: -0.1700
Data Index: 2301396 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.2437. Min Act: -0.1700
Data Index: 801390 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.2750. Min Act: -0.1700
Data Index: 1511232 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6812. Min Range: -7.6812
Max Act: 7.2437. Min Act: -0.1700
Data Index: 5981182 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19