Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0146. Min Range: -6.0146
Max Act: 6.0146. Min Act: -0.1700
Data Index: 6521422 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.9834. Min Act: -0.1700
Data Index: 8205724 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.8896. Min Act: -0.1700
Data Index: 4777557 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.8584. Min Act: -0.1700
Data Index: 2747636 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.8271. Min Act: -0.1700
Data Index: 1284573 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.8271. Min Act: -0.1700
Data Index: 1284589 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1284596 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1701483 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7646. Min Act: -0.1700
Data Index: 6521427 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7646. Min Act: -0.1700
Data Index: 2524270 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7334. Min Act: -0.1700
Data Index: 4421780 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7646. Min Act: -0.1700
Data Index: 4260530 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7334. Min Act: -0.1700
Data Index: 8713323 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7334. Min Act: -0.1700
Data Index: 6150467 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7021. Min Act: -0.1700
Data Index: 6521435 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7021. Min Act: -0.1700
Data Index: 1284575 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7021. Min Act: -0.1700
Data Index: 2197640 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7021. Min Act: -0.1700
Data Index: 558409 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7021. Min Act: -0.1700
Data Index: 6150477 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0146. Min Range: -6.0146
Max Act: 5.7021. Min Act: -0.1700
Data Index: 4126398 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19