Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0971. Min Range: -5.0971
Max Act: 5.0971. Min Act: -0.1700
Data Index: 1461563 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.9721. Min Act: -0.1700
Data Index: 1125845 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.9721. Min Act: -0.1700
Data Index: 146437 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.9721. Min Act: -0.1700
Data Index: 6582447 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.9408. Min Act: -0.1700
Data Index: 608223 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.9096. Min Act: -0.1700
Data Index: 2492433 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8783. Min Act: -0.1700
Data Index: 8067823 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8783. Min Act: -0.1700
Data Index: 6911316 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8471. Min Act: -0.1700
Data Index: 5818124 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8471. Min Act: -0.1700
Data Index: 1450507 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8471. Min Act: -0.1700
Data Index: 8382424 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8783. Min Act: -0.1700
Data Index: 7091908 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.7846. Min Act: -0.1700
Data Index: 2975919 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.8158. Min Act: -0.1700
Data Index: 4163716 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.7846. Min Act: -0.1700
Data Index: 3173715 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.7846. Min Act: -0.1700
Data Index: 5159245 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.7846. Min Act: -0.1700
Data Index: 7343479 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.7221. Min Act: -0.1700
Data Index: 1656244 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.7533. Min Act: -0.1700
Data Index: 2901999 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0971. Min Range: -5.0971
Max Act: 4.6908. Min Act: -0.1700
Data Index: 4387079 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19