Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.8046. Min Act: -0.1700
Data Index: 2541847 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.6171. Min Act: -0.1700
Data Index: 7566411 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.6171. Min Act: -0.1700
Data Index: 3287683 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.3046. Min Act: -0.1700
Data Index: 3464893 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.3046. Min Act: -0.1700
Data Index: 7907043 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.2421. Min Act: -0.1700
Data Index: 6593972 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.1796. Min Act: -0.1700
Data Index: 3221315 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.1796. Min Act: -0.1700
Data Index: 7992012 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.1171. Min Act: -0.1700
Data Index: 1091908 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.1171. Min Act: -0.1700
Data Index: 6324134 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.1171. Min Act: -0.1700
Data Index: 4794990 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.0546. Min Act: -0.1700
Data Index: 4295062 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8046. Min Range: -9.8046
Max Act: 9.0546. Min Act: -0.1700
Data Index: 7476293 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.9921. Min Act: -0.1700
Data Index: 4551914 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.9296. Min Act: -0.1700
Data Index: 8462300 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.8671. Min Act: -0.1700
Data Index: 6306974 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.8671. Min Act: -0.1700
Data Index: 1087200 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.8046. Min Act: -0.1700
Data Index: 6559131 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.8046. Min Act: -0.1700
Data Index: 7600675 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8046. Min Range: -9.8046
Max Act: 8.8046. Min Act: -0.1700
Data Index: 4796035 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19