Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.7507. Min Act: -0.1700
Data Index: 1559754 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5319. Min Act: -0.1700
Data Index: 6140469 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 4110578 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 7772479 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 2708858 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 768509 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 2695903 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 3583148 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 667739 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 5283797 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 5486151 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 6416030 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 990097 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 7068649 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 3991490 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 2105640 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 3301491 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 5223231 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 4333666 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3444. Min Act: -0.1700
Data Index: 3014896 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19