Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4172 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.7350. Min Act: -0.1700
Data Index: 2584839 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6710. Min Act: -0.1700
Data Index: 4374593 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6710. Min Act: -0.1700
Data Index: 243105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6550. Min Act: -0.1700
Data Index: 4583652 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6710. Min Act: -0.1700
Data Index: 1232658 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6550. Min Act: -0.1700
Data Index: 6389053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6068. Min Act: -0.1700
Data Index: 40481 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6229. Min Act: -0.1700
Data Index: 6252627 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6229. Min Act: -0.1700
Data Index: 1098681 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.6068. Min Act: -0.1700
Data Index: 2975828 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5907. Min Act: -0.1700
Data Index: 7292218 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5746. Min Act: -0.1700
Data Index: 7788989 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5746. Min Act: -0.1700
Data Index: 1090163 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 5856216 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 4840466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 3129210 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 5420407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 7226932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 5689555 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7350. Min Range: -2.7350
Max Act: 2.5585. Min Act: -0.1700
Data Index: 2474336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19