Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.5425. Min Act: -0.1700
Data Index: 2142885 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.5112. Min Act: -0.1700
Data Index: 8704079 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.4800. Min Act: -0.1700
Data Index: 1905095 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.3862. Min Act: -0.1700
Data Index: 6803988 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.2612. Min Act: -0.1700
Data Index: 3181022 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.1987. Min Act: -0.1700
Data Index: 4915238 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.1674. Min Act: -0.1700
Data Index: 5989618 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.1674. Min Act: -0.1700
Data Index: 327616 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.1362. Min Act: -0.1700
Data Index: 2935824 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.1362. Min Act: -0.1700
Data Index: 2159906 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.1362. Min Act: -0.1700
Data Index: 4289474 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.0424. Min Act: -0.1700
Data Index: 5670708 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.0737. Min Act: -0.1700
Data Index: 787079 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.0424. Min Act: -0.1700
Data Index: 5588809 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.0424. Min Act: -0.1700
Data Index: 696224 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.0112. Min Act: -0.1700
Data Index: 4198683 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5425. Min Range: -4.5425
Max Act: 4.0112. Min Act: -0.1700
Data Index: 7220371 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5425. Min Range: -4.5425
Max Act: 3.9486. Min Act: -0.1700
Data Index: 2542815 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5425. Min Range: -4.5425
Max Act: 3.9799. Min Act: -0.1700
Data Index: 4218410 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5425. Min Range: -4.5425
Max Act: 3.9799. Min Act: -0.1700
Data Index: 469449 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19