Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 184 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1276. Min Range: -6.1276
Max Act: 6.1276. Min Act: -0.1700
Data Index: 4424085 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.8463. Min Act: -0.1700
Data Index: 2899052 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.8776. Min Act: -0.1700
Data Index: 8791804 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.7526. Min Act: -0.1700
Data Index: 8542267 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.7526. Min Act: -0.1700
Data Index: 4248244 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.7526. Min Act: -0.1700
Data Index: 4671862 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.6901. Min Act: -0.1700
Data Index: 6242236 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5963. Min Act: -0.1700
Data Index: 552659 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5651. Min Act: -0.1700
Data Index: 4893532 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5651. Min Act: -0.1700
Data Index: 5692119 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5338. Min Act: -0.1700
Data Index: 2137481 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5338. Min Act: -0.1700
Data Index: 8381847 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5338. Min Act: -0.1700
Data Index: 8553421 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5338. Min Act: -0.1700
Data Index: 6241381 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5338. Min Act: -0.1700
Data Index: 2072041 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.5338. Min Act: -0.1700
Data Index: 8506937 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.4713. Min Act: -0.1700
Data Index: 3392311 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.4713. Min Act: -0.1700
Data Index: 5964764 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.4713. Min Act: -0.1700
Data Index: 16519 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1276. Min Range: -6.1276
Max Act: 5.4401. Min Act: -0.1700
Data Index: 5150576 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19