Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1895. Min Range: -10.1895
Max Act: 10.1895. Min Act: -0.1700
Data Index: 6901415 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1895. Min Range: -10.1895
Max Act: 10.0645. Min Act: -0.1700
Data Index: 5575063 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1895. Min Range: -10.1895
Max Act: 10.0020. Min Act: -0.1700
Data Index: 5788817 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.9395. Min Act: -0.1700
Data Index: 1140969 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8770. Min Act: -0.1700
Data Index: 2490592 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8770. Min Act: -0.1700
Data Index: 5577168 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8770. Min Act: -0.1700
Data Index: 2942023 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8770. Min Act: -0.1700
Data Index: 1977471 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8770. Min Act: -0.1700
Data Index: 2309719 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8145. Min Act: -0.1700
Data Index: 8324717 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8145. Min Act: -0.1700
Data Index: 6403472 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8145. Min Act: -0.1700
Data Index: 6063780 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.7520. Min Act: -0.1700
Data Index: 8605046 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.8145. Min Act: -0.1700
Data Index: 4300165 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.7520. Min Act: -0.1700
Data Index: 136364 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.7520. Min Act: -0.1700
Data Index: 7581368 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.6895. Min Act: -0.1700
Data Index: 101357 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.6895. Min Act: -0.1700
Data Index: 764459 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.6895. Min Act: -0.1700
Data Index: 5916651 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1895. Min Range: -10.1895
Max Act: 9.6895. Min Act: -0.1700
Data Index: 5378368 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19