Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6037 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.6507. Min Act: -0.1700
Data Index: 4399452 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.6350. Min Act: -0.1700
Data Index: 559474 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.6350. Min Act: -0.1700
Data Index: 3997580 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.6194. Min Act: -0.1700
Data Index: 6779971 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5881. Min Act: -0.1700
Data Index: 2241623 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5881. Min Act: -0.1700
Data Index: 4358203 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5881. Min Act: -0.1700
Data Index: 3431 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5881. Min Act: -0.1700
Data Index: 6918529 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5881. Min Act: -0.1700
Data Index: 3664909 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5724. Min Act: -0.1700
Data Index: 2536000 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5724. Min Act: -0.1700
Data Index: 7155453 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5568. Min Act: -0.1700
Data Index: 3357133 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5568. Min Act: -0.1700
Data Index: 6521857 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5568. Min Act: -0.1700
Data Index: 207025 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5568. Min Act: -0.1700
Data Index: 2042022 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5255. Min Act: -0.1700
Data Index: 3357108 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5411. Min Act: -0.1700
Data Index: 1330681 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5255. Min Act: -0.1700
Data Index: 2274750 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5411. Min Act: -0.1700
Data Index: 392480 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6507. Min Range: -3.6507
Max Act: 3.5255. Min Act: -0.1700
Data Index: 1478525 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19