Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.7098. Min Act: -0.1700
Data Index: 1524138 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4911. Min Act: -0.1700
Data Index: 1403413 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 8213123 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4367495 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4286. Min Act: -0.1700
Data Index: 6966518 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4364645 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4286. Min Act: -0.1700
Data Index: 1550692 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3973. Min Act: -0.1700
Data Index: 3735122 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3660. Min Act: -0.1700
Data Index: 8242570 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3348. Min Act: -0.1700
Data Index: 6549620 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3348. Min Act: -0.1700
Data Index: 851267 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3348. Min Act: -0.1700
Data Index: 6526080 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3035. Min Act: -0.1700
Data Index: 989233 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3035. Min Act: -0.1700
Data Index: 2185596 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3035. Min Act: -0.1700
Data Index: 336966 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3035. Min Act: -0.1700
Data Index: 5485325 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 4718825 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3035. Min Act: -0.1700
Data Index: 5748257 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 6124965 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 2618044 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19