Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 1202385 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5420. Min Act: -0.1700
Data Index: 3417883 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3545. Min Act: -0.1700
Data Index: 541180 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 2839429 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2608. Min Act: -0.1700
Data Index: 2833609 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2295. Min Act: -0.1700
Data Index: 5850093 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2295. Min Act: -0.1700
Data Index: 7295554 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.1983. Min Act: -0.1700
Data Index: 5653458 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.1358. Min Act: -0.1700
Data Index: 3191469 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.1358. Min Act: -0.1700
Data Index: 4280804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.1358. Min Act: -0.1700
Data Index: 22668 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.1045. Min Act: -0.1700
Data Index: 3841991 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0733. Min Act: -0.1700
Data Index: 8340124 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0733. Min Act: -0.1700
Data Index: 6851521 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0420. Min Act: -0.1700
Data Index: 1182867 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0420. Min Act: -0.1700
Data Index: 2237670 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5112821 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0108. Min Act: -0.1700
Data Index: 1366754 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.0108. Min Act: -0.1700
Data Index: 1889972 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6983. Min Range: -5.6983
Max Act: 4.9795. Min Act: -0.1700
Data Index: 1549805 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19