Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.8357. Min Act: -0.1700
Data Index: 6714026 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.7107. Min Act: -0.1700
Data Index: 3323121 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.5544. Min Act: -0.1700
Data Index: 2689628 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.5232. Min Act: -0.1700
Data Index: 5966250 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.4919. Min Act: -0.1700
Data Index: 6391276 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.4294. Min Act: -0.1700
Data Index: 3178302 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.4294. Min Act: -0.1700
Data Index: 3032213 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3982. Min Act: -0.1700
Data Index: 1792474 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3982. Min Act: -0.1700
Data Index: 6985670 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3669. Min Act: -0.1700
Data Index: 2298908 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3669. Min Act: -0.1700
Data Index: 6468911 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3044. Min Act: -0.1700
Data Index: 2664566 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3044. Min Act: -0.1700
Data Index: 8539900 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3357. Min Act: -0.1700
Data Index: 6858330 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3357. Min Act: -0.1700
Data Index: 416556 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3357. Min Act: -0.1700
Data Index: 3555143 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3044. Min Act: -0.1700
Data Index: 7608461 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3044. Min Act: -0.1700
Data Index: 910470 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3044. Min Act: -0.1700
Data Index: 274779 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8357. Min Range: -4.8357
Max Act: 4.3044. Min Act: -0.1700
Data Index: 5715935 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19