Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0240. Min Range: -9.0240
Max Act: 9.0240. Min Act: -0.1700
Data Index: 1181148 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.7740. Min Act: -0.1700
Data Index: 7492262 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.6490. Min Act: -0.1700
Data Index: 726768 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.6490. Min Act: -0.1700
Data Index: 1038493 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.5865. Min Act: -0.1700
Data Index: 8657671 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.5240. Min Act: -0.1700
Data Index: 52294 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.5240. Min Act: -0.1700
Data Index: 1293371 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.5240. Min Act: -0.1700
Data Index: 3872912 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.4615. Min Act: -0.1700
Data Index: 2342033 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.4615. Min Act: -0.1700
Data Index: 7016488 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.4615. Min Act: -0.1700
Data Index: 6699577 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.3990. Min Act: -0.1700
Data Index: 1149237 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.3365. Min Act: -0.1700
Data Index: 3910149 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.3365. Min Act: -0.1700
Data Index: 3750420 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.2740. Min Act: -0.1700
Data Index: 7707476 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 8072421 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 3632229 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 7203323 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 23301 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0240. Min Range: -9.0240
Max Act: 8.1490. Min Act: -0.1700
Data Index: 3820898 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19