Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2526. Min Range: -11.2526
Max Act: 11.2526. Min Act: -0.1700
Data Index: 4043247 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2526. Min Range: -11.2526
Max Act: 11.0026. Min Act: -0.1700
Data Index: 8428970 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2526. Min Range: -11.2526
Max Act: 11.0026. Min Act: -0.1700
Data Index: 86461 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.8776. Min Act: -0.1700
Data Index: 2699731 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.9401. Min Act: -0.1699
Data Index: 4575501 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.8151. Min Act: -0.1700
Data Index: 8327970 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.7526. Min Act: -0.1700
Data Index: 6685759 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.7526. Min Act: -0.1700
Data Index: 8706960 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.7526. Min Act: -0.1700
Data Index: 8014656 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6901. Min Act: -0.1700
Data Index: 7909461 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6901. Min Act: -0.1700
Data Index: 1474448 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6901. Min Act: -0.1700
Data Index: 7472220 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6901. Min Act: -0.1700
Data Index: 7212492 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6276. Min Act: -0.1700
Data Index: 5097617 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6276. Min Act: -0.1700
Data Index: 2407396 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.6276. Min Act: -0.1700
Data Index: 816381 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.5651. Min Act: -0.1700
Data Index: 3676486 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.5026. Min Act: -0.1700
Data Index: 132379 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.5026. Min Act: -0.1700
Data Index: 6685762 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2526. Min Range: -11.2526
Max Act: 10.5026. Min Act: -0.1700
Data Index: 7596596 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19