Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4923 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.6060. Min Act: -0.1700
Data Index: 915643 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.5747. Min Act: -0.1700
Data Index: 2170497 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.5435. Min Act: -0.1700
Data Index: 503258 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.5122. Min Act: -0.1700
Data Index: 97454 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.4497. Min Act: -0.1700
Data Index: 4496774 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.4185. Min Act: -0.1700
Data Index: 584733 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.4185. Min Act: -0.1700
Data Index: 4560224 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.4185. Min Act: -0.1700
Data Index: 8155018 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 4154921 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 4408487 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 5365792 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 8276537 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 1531850 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 8545167 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3872. Min Act: -0.1700
Data Index: 6250314 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3560. Min Act: -0.1700
Data Index: 3295968 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3247. Min Act: -0.1700
Data Index: 584734 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3247. Min Act: -0.1700
Data Index: 2887278 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3247. Min Act: -0.1700
Data Index: 980723 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6060. Min Range: -5.6060
Max Act: 5.3247. Min Act: -0.1700
Data Index: 6830698 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19