Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4038 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9494. Min Act: -0.1700
Data Index: 7662256 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9494. Min Act: -0.1700
Data Index: 5200302 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9494. Min Act: -0.1700
Data Index: 4655628 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9494. Min Act: -0.1700
Data Index: 8023623 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9182. Min Act: -0.1700
Data Index: 7887235 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3534100 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9182. Min Act: -0.1700
Data Index: 8511825 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8869. Min Act: -0.1700
Data Index: 4174754 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.9182. Min Act: -0.1700
Data Index: 947561 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3178551 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8869. Min Act: -0.1700
Data Index: 1789247 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8557. Min Act: -0.1700
Data Index: 8093389 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8557. Min Act: -0.1700
Data Index: 8483987 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8557. Min Act: -0.1700
Data Index: 6410186 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8557. Min Act: -0.1700
Data Index: 6437171 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8557. Min Act: -0.1700
Data Index: 4231266 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8557. Min Act: -0.1700
Data Index: 7526285 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8244. Min Act: -0.1700
Data Index: 4417724 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8244. Min Act: -0.1700
Data Index: 2815616 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9494. Min Range: -5.9494
Max Act: 5.8244. Min Act: -0.1700
Data Index: 7843104 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19