Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.8280. Min Act: -0.1700
Data Index: 1089319 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.7030. Min Act: -0.1700
Data Index: 7346172 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.7030. Min Act: -0.1700
Data Index: 4469015 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.7030. Min Act: -0.1700
Data Index: 6667805 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.5780. Min Act: -0.1700
Data Index: 8337861 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.6092. Min Act: -0.1700
Data Index: 36830 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.5467. Min Act: -0.1700
Data Index: 6216158 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.4842. Min Act: -0.1700
Data Index: 2676807 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.3905. Min Act: -0.1700
Data Index: 3066654 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.3905. Min Act: -0.1700
Data Index: 7761961 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.3592. Min Act: -0.1700
Data Index: 7086163 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.3280. Min Act: -0.1700
Data Index: 4858590 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2655. Min Act: -0.1700
Data Index: 7994935 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2967. Min Act: -0.1700
Data Index: 6551174 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2967. Min Act: -0.1700
Data Index: 7940572 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2655. Min Act: -0.1700
Data Index: 5093349 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2342. Min Act: -0.1700
Data Index: 8733696 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2030. Min Act: -0.1700
Data Index: 1388372 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2030. Min Act: -0.1700
Data Index: 2745506 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8280. Min Range: -4.8280
Max Act: 4.2030. Min Act: -0.1700
Data Index: 2390580 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19