Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.8576. Min Act: -0.1700
Data Index: 5007923 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.7326. Min Act: -0.1700
Data Index: 8183117 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.7326. Min Act: -0.1700
Data Index: 7362030 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.7326. Min Act: -0.1700
Data Index: 5701196 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.7014. Min Act: -0.1700
Data Index: 527725 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.7326. Min Act: -0.1700
Data Index: 4482695 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.6701. Min Act: -0.1700
Data Index: 8249423 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.6701. Min Act: -0.1700
Data Index: 8493230 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5846089 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5770315 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.5764. Min Act: -0.1700
Data Index: 7899441 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.5451. Min Act: -0.1700
Data Index: 8810438 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.5451. Min Act: -0.1700
Data Index: 7266835 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4826. Min Act: -0.1700
Data Index: 3308348 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4826. Min Act: -0.1700
Data Index: 6335449 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4826. Min Act: -0.1700
Data Index: 4545303 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4826. Min Act: -0.1700
Data Index: 232723 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4826. Min Act: -0.1700
Data Index: 552659 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4826. Min Act: -0.1700
Data Index: 6990220 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8576. Min Range: -5.8576
Max Act: 5.4514. Min Act: -0.1700
Data Index: 6844812 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19