Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.8833. Min Act: -0.1700
Data Index: 455658 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7895. Min Act: -0.1700
Data Index: 5270824 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7895. Min Act: -0.1700
Data Index: 2195995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7582. Min Act: -0.1700
Data Index: 2360601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7582. Min Act: -0.1700
Data Index: 4412338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7582. Min Act: -0.1700
Data Index: 4192809 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7582. Min Act: -0.1700
Data Index: 4618526 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7582. Min Act: -0.1700
Data Index: 6948557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7269. Min Act: -0.1700
Data Index: 4190064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7269. Min Act: -0.1700
Data Index: 8755163 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7269. Min Act: -0.1700
Data Index: 323013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 3739913 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 351087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 3542197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 4198013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 1616353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.7269. Min Act: -0.1700
Data Index: 2850462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 4277099 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 209308 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8833. Min Range: -3.8833
Max Act: 3.6956. Min Act: -0.1700
Data Index: 4487882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19