Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.6690. Min Act: -0.1700
Data Index: 8636533 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.4815. Min Act: -0.1700
Data Index: 407496 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.4190. Min Act: -0.1700
Data Index: 2612612 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.4190. Min Act: -0.1700
Data Index: 7776404 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.3565. Min Act: -0.1700
Data Index: 4096763 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.3565. Min Act: -0.1700
Data Index: 5496244 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.3565. Min Act: -0.1700
Data Index: 458702 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.2940. Min Act: -0.1700
Data Index: 8741625 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.2940. Min Act: -0.1700
Data Index: 5325378 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1690. Min Act: -0.1700
Data Index: 1413836 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1690. Min Act: -0.1700
Data Index: 399172 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1690. Min Act: -0.1700
Data Index: 2032346 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1690. Min Act: -0.1700
Data Index: 1615175 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1065. Min Act: -0.1700
Data Index: 5172625 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1065. Min Act: -0.1700
Data Index: 7063787 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.1065. Min Act: -0.1700
Data Index: 7477646 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.0440. Min Act: -0.1700
Data Index: 8289095 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.0440. Min Act: -0.1700
Data Index: 8725813 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.0440. Min Act: -0.1700
Data Index: 209814 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6690. Min Range: -8.6690
Max Act: 8.0440. Min Act: -0.1700
Data Index: 2111453 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19