Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2499 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.3559. Min Act: -0.1700
Data Index: 2545643 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.3088. Min Act: -0.1700
Data Index: 2518071 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.2774. Min Act: -0.1700
Data Index: 4723679 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.2617. Min Act: -0.1700
Data Index: 7724280 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.2460. Min Act: -0.1700
Data Index: 7820770 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1988. Min Act: -0.1700
Data Index: 5927806 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1988. Min Act: -0.1700
Data Index: 7603666 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1831. Min Act: -0.1700
Data Index: 6128773 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1988. Min Act: -0.1700
Data Index: 7810375 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1674. Min Act: -0.1700
Data Index: 4232562 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1674. Min Act: -0.1700
Data Index: 5927314 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1674. Min Act: -0.1700
Data Index: 6669615 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1359. Min Act: -0.1700
Data Index: 161120 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1359. Min Act: -0.1700
Data Index: 7126483 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.1044. Min Act: -0.1700
Data Index: 5790198 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.0886. Min Act: -0.1700
Data Index: 3966484 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.0886. Min Act: -0.1700
Data Index: 360869 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.0886. Min Act: -0.1700
Data Index: 8369843 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.0728. Min Act: -0.1700
Data Index: 5956849 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3559. Min Range: -3.3559
Max Act: 3.0728. Min Act: -0.1700
Data Index: 6848544 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19