Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2239 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 6528563 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.5175. Min Act: -0.1700
Data Index: 600729 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.5175. Min Act: -0.1700
Data Index: 5483504 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.5175. Min Act: -0.1700
Data Index: 1582054 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 6345003 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 6027345 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 150488 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 2491454 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 191137 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.3925. Min Act: -0.1700
Data Index: 5371570 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 948288 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 5218480 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 4798851 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.3925. Min Act: -0.1700
Data Index: 4747534 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 4542657 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 507787 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.5175. Min Act: -0.1700
Data Index: 3589645 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.3925. Min Act: -0.1700
Data Index: 3176772 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 563247 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5175. Min Range: -9.5175
Max Act: 9.4550. Min Act: -0.1700
Data Index: 1880296 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19