Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1830 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.8911. Min Act: -0.1700
Data Index: 1616392 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.9223. Min Act: -0.1700
Data Index: 283521 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.8286. Min Act: -0.1700
Data Index: 7756989 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7973. Min Act: -0.1700
Data Index: 7880946 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7973. Min Act: -0.1700
Data Index: 792728 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7973. Min Act: -0.1700
Data Index: 1099730 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7973. Min Act: -0.1700
Data Index: 1986247 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7973. Min Act: -0.1700
Data Index: 7427467 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7973. Min Act: -0.1700
Data Index: 8715075 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7348. Min Act: -0.1700
Data Index: 1616391 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.6723. Min Act: -0.1700
Data Index: 1255285 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7348. Min Act: -0.1700
Data Index: 1960028 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7036. Min Act: -0.1700
Data Index: 5515076 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7348. Min Act: -0.1700
Data Index: 240609 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7036. Min Act: -0.1700
Data Index: 1616390 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.7036. Min Act: -0.1700
Data Index: 8134389 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.6723. Min Act: -0.1700
Data Index: 4340384 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.6723. Min Act: -0.1700
Data Index: 8165280 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.6723. Min Act: -0.1700
Data Index: 8160343 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9223. Min Range: -4.9223
Max Act: 4.6098. Min Act: -0.1700
Data Index: 5087954 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19