Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3683 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.1052. Min Act: -0.1700
Data Index: 2592028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.0740. Min Act: -0.1700
Data Index: 63956 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.0427. Min Act: -0.1700
Data Index: 4225281 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.0427. Min Act: -0.1700
Data Index: 4741681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.0427. Min Act: -0.1700
Data Index: 7187731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.0427. Min Act: -0.1700
Data Index: 2155439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1052. Min Range: -5.1052
Max Act: 5.0427. Min Act: -0.1700
Data Index: 4032781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.9802. Min Act: -0.1700
Data Index: 3607272 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.9802. Min Act: -0.1700
Data Index: 2129800 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.9490. Min Act: -0.1700
Data Index: 1659010 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.9490. Min Act: -0.1700
Data Index: 3410321 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.9177. Min Act: -0.1700
Data Index: 7139421 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.9177. Min Act: -0.1700
Data Index: 7869547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.8865. Min Act: -0.1700
Data Index: 6904951 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.8552. Min Act: -0.1700
Data Index: 3927442 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.8240. Min Act: -0.1700
Data Index: 7149231 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.8552. Min Act: -0.1700
Data Index: 3673201 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.8240. Min Act: -0.1700
Data Index: 7365978 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.8240. Min Act: -0.1700
Data Index: 8341357 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1052. Min Range: -5.1052
Max Act: 4.7927. Min Act: -0.1700
Data Index: 8504357 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19