Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2303 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3479. Min Act: -0.1700
Data Index: 8725355 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3322. Min Act: -0.1700
Data Index: 3130519 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2851. Min Act: -0.1700
Data Index: 6938552 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2851. Min Act: -0.1700
Data Index: 8511729 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2851. Min Act: -0.1700
Data Index: 2646759 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2694. Min Act: -0.1700
Data Index: 1552619 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2694. Min Act: -0.1700
Data Index: 4991831 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 7576295 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6605064 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2223. Min Act: -0.1700
Data Index: 1228121 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2380. Min Act: -0.1700
Data Index: 4522183 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 1627657 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 7080074 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2380. Min Act: -0.1700
Data Index: 8821391 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.1908. Min Act: -0.1700
Data Index: 3035018 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2223. Min Act: -0.1700
Data Index: 215628 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2223. Min Act: -0.1700
Data Index: 2546166 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.1908. Min Act: -0.1700
Data Index: 8221604 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.1908. Min Act: -0.1700
Data Index: 3262797 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2066. Min Act: -0.1700
Data Index: 3286460 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19