Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.6636. Min Act: -0.1700
Data Index: 2949408 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.6475. Min Act: -0.1700
Data Index: 3369478 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.6315. Min Act: -0.1700
Data Index: 5569265 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5993. Min Act: -0.1700
Data Index: 5971113 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5993. Min Act: -0.1700
Data Index: 1853021 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5509. Min Act: -0.1700
Data Index: 7798108 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5509. Min Act: -0.1700
Data Index: 7816137 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5509. Min Act: -0.1700
Data Index: 2855292 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5348. Min Act: -0.1700
Data Index: 1199812 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5348. Min Act: -0.1700
Data Index: 2852684 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5186. Min Act: -0.1700
Data Index: 206185 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5024. Min Act: -0.1700
Data Index: 495194 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.4862. Min Act: -0.1700
Data Index: 4587182 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5024. Min Act: -0.1700
Data Index: 2151121 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5024. Min Act: -0.1700
Data Index: 7272370 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5024. Min Act: -0.1700
Data Index: 3459654 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.5024. Min Act: -0.1700
Data Index: 3724755 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.4862. Min Act: -0.1700
Data Index: 4571486 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.4700. Min Act: -0.1700
Data Index: 1978970 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6636. Min Range: -2.6636
Max Act: 2.4862. Min Act: -0.1700
Data Index: 6593440 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19