Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 394 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.5711. Min Act: -0.1700
Data Index: 5196033 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.3211. Min Act: -0.1700
Data Index: 8690919 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.3211. Min Act: -0.1700
Data Index: 428265 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.2586. Min Act: -0.1700
Data Index: 7526462 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.1336. Min Act: -0.1700
Data Index: 6411083 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.1336. Min Act: -0.1700
Data Index: 542237 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.0711. Min Act: -0.1700
Data Index: 7498793 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.0711. Min Act: -0.1700
Data Index: 1180154 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.0711. Min Act: -0.1700
Data Index: 6768116 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.0086. Min Act: -0.1700
Data Index: 6846847 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5711. Min Range: -9.5711
Max Act: 9.0086. Min Act: -0.1700
Data Index: 848442 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8836. Min Act: -0.1700
Data Index: 6311558 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8836. Min Act: -0.1700
Data Index: 3204025 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8836. Min Act: -0.1700
Data Index: 4042462 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8836. Min Act: -0.1700
Data Index: 5836635 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8836. Min Act: -0.1700
Data Index: 5761165 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8836. Min Act: -0.1700
Data Index: 8137940 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8211. Min Act: -0.1700
Data Index: 8365979 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8211. Min Act: -0.1700
Data Index: 5590940 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5711. Min Range: -9.5711
Max Act: 8.8211. Min Act: -0.1700
Data Index: 8587684 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19