Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1356. Min Range: -6.1356
Max Act: 6.1356. Min Act: -0.1700
Data Index: 2754576 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1356. Min Range: -6.1356
Max Act: 6.1044. Min Act: -0.1700
Data Index: 5172193 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1356. Min Range: -6.1356
Max Act: 6.0419. Min Act: -0.1700
Data Index: 3833200 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.9794. Min Act: -0.1700
Data Index: 8463683 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.9169. Min Act: -0.1700
Data Index: 111712 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.9169. Min Act: -0.1700
Data Index: 4201021 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8856. Min Act: -0.1700
Data Index: 2845693 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.9169. Min Act: -0.1700
Data Index: 1457027 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.9169. Min Act: -0.1700
Data Index: 6669325 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8856. Min Act: -0.1700
Data Index: 725396 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8856. Min Act: -0.1700
Data Index: 1317440 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8544. Min Act: -0.1700
Data Index: 5289416 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8544. Min Act: -0.1700
Data Index: 8277713 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8231. Min Act: -0.1700
Data Index: 630491 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8231. Min Act: -0.1700
Data Index: 7265320 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.8231. Min Act: -0.1700
Data Index: 3352656 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.7919. Min Act: -0.1700
Data Index: 8654754 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.7919. Min Act: -0.1700
Data Index: 6352639 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.7919. Min Act: -0.1700
Data Index: 1124389 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1356. Min Range: -6.1356
Max Act: 5.7919. Min Act: -0.1700
Data Index: 2666494 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19