Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.5527. Min Act: -0.1700
Data Index: 700815 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.4430. Min Act: -0.1700
Data Index: 3739285 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3960. Min Act: -0.1700
Data Index: 8087321 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 1136206 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 3467414 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 1705356 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 3926314 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 3335830 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 6192 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3333. Min Act: -0.1700
Data Index: 6934673 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3490. Min Act: -0.1700
Data Index: 536374 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3019. Min Act: -0.1700
Data Index: 179023 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3176. Min Act: -0.1700
Data Index: 3668611 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3176. Min Act: -0.1700
Data Index: 2024276 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3019. Min Act: -0.1700
Data Index: 8390700 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3019. Min Act: -0.1700
Data Index: 4230948 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.2862. Min Act: -0.1700
Data Index: 5346479 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.3019. Min Act: -0.1700
Data Index: 1136207 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.2705. Min Act: -0.1700
Data Index: 1471738 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5527. Min Range: -3.5527
Max Act: 3.2705. Min Act: -0.1700
Data Index: 5599931 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19