Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3277. Min Range: -9.3277
Max Act: 9.3277. Min Act: -0.1700
Data Index: 3754547 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3277. Min Range: -9.3277
Max Act: 9.1402. Min Act: -0.1700
Data Index: 7084440 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3277. Min Range: -9.3277
Max Act: 9.1402. Min Act: -0.1700
Data Index: 6886870 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3277. Min Range: -9.3277
Max Act: 9.0777. Min Act: -0.1700
Data Index: 4305866 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.9527. Min Act: -0.1700
Data Index: 7838665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.9527. Min Act: -0.1700
Data Index: 7985439 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8902. Min Act: -0.1700
Data Index: 5282980 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8902. Min Act: -0.1700
Data Index: 2810385 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 3013482 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 6855288 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 1246060 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 2611359 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 4392260 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 4140486 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 5034196 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.7652. Min Act: -0.1700
Data Index: 2083814 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.7652. Min Act: -0.1700
Data Index: 5546117 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.8277. Min Act: -0.1700
Data Index: 7842072 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.7652. Min Act: -0.1700
Data Index: 310047 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3277. Min Range: -9.3277
Max Act: 8.7652. Min Act: -0.1700
Data Index: 5608671 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19