Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 741 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.2983. Min Act: -0.1700
Data Index: 1977961 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.2045. Min Act: -0.1700
Data Index: 1348132 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.1420. Min Act: -0.1700
Data Index: 7216904 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.1108. Min Act: -0.1700
Data Index: 4456981 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.0483. Min Act: -0.1700
Data Index: 6542580 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.0483. Min Act: -0.1700
Data Index: 6695848 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2983. Min Range: -7.2983
Max Act: 7.0170. Min Act: -0.1700
Data Index: 7125200 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.9545. Min Act: -0.1700
Data Index: 4824265 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.9545. Min Act: -0.1700
Data Index: 3982705 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.9545. Min Act: -0.1700
Data Index: 6800629 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.9233. Min Act: -0.1700
Data Index: 5975252 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8920. Min Act: -0.1700
Data Index: 5084296 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8920. Min Act: -0.1700
Data Index: 6549193 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8608. Min Act: -0.1700
Data Index: 3435232 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8608. Min Act: -0.1700
Data Index: 6520716 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8608. Min Act: -0.1700
Data Index: 4078745 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.7983. Min Act: -0.1700
Data Index: 71996 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8295. Min Act: -0.1700
Data Index: 7318335 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8295. Min Act: -0.1700
Data Index: 4583968 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2983. Min Range: -7.2983
Max Act: 6.8295. Min Act: -0.1700
Data Index: 5056607 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19