Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.3162. Min Act: -0.1700
Data Index: 7625618 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.1286. Min Act: -0.1700
Data Index: 4666599 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0974. Min Act: -0.1700
Data Index: 7259634 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0661. Min Act: -0.1700
Data Index: 854411 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0974. Min Act: -0.1700
Data Index: 3368827 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.1286. Min Act: -0.1700
Data Index: 1847566 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0974. Min Act: -0.1700
Data Index: 6331920 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0974. Min Act: -0.1700
Data Index: 921246 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0661. Min Act: -0.1700
Data Index: 6331919 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0349. Min Act: -0.1700
Data Index: 2816143 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0349. Min Act: -0.1700
Data Index: 6950145 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0036. Min Act: -0.1700
Data Index: 4656351 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0036. Min Act: -0.1700
Data Index: 8016717 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0036. Min Act: -0.1700
Data Index: 8153614 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3162. Min Range: -4.3162
Max Act: 4.0036. Min Act: -0.1700
Data Index: 3722748 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3162. Min Range: -4.3162
Max Act: 3.9723. Min Act: -0.1700
Data Index: 694649 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3162. Min Range: -4.3162
Max Act: 3.9411. Min Act: -0.1700
Data Index: 3988642 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3162. Min Range: -4.3162
Max Act: 3.9411. Min Act: -0.1700
Data Index: 1086096 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3162. Min Range: -4.3162
Max Act: 3.9723. Min Act: -0.1700
Data Index: 6052182 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3162. Min Range: -4.3162
Max Act: 3.9723. Min Act: -0.1700
Data Index: 5954229 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19