Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.6136. Min Act: -0.1700
Data Index: 91687 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.4886. Min Act: -0.1700
Data Index: 8779863 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.4261. Min Act: -0.1700
Data Index: 2467343 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.3636. Min Act: -0.1700
Data Index: 2522547 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.3011. Min Act: -0.1700
Data Index: 3683782 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6412930 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.2386. Min Act: -0.1700
Data Index: 8237925 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.2698. Min Act: -0.1700
Data Index: 4160690 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.2386. Min Act: -0.1700
Data Index: 2197190 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.1761. Min Act: -0.1700
Data Index: 1854727 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0823. Min Act: -0.1700
Data Index: 3900776 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0511. Min Act: -0.1700
Data Index: 370743 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0511. Min Act: -0.1700
Data Index: 8022364 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0198. Min Act: -0.1700
Data Index: 8365 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0511. Min Act: -0.1700
Data Index: 7050973 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0198. Min Act: -0.1700
Data Index: 141391 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.9886. Min Act: -0.1700
Data Index: 2119654 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.9886. Min Act: -0.1700
Data Index: 1154849 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.9573. Min Act: -0.1700
Data Index: 3532413 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.9573. Min Act: -0.1700
Data Index: 7511928 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19