Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1965 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.3020. Min Act: -0.1700
Data Index: 3631685 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2708. Min Act: -0.1700
Data Index: 6914921 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2708. Min Act: -0.1700
Data Index: 5767431 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2395. Min Act: -0.1700
Data Index: 350606 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2395. Min Act: -0.1700
Data Index: 2994645 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2395. Min Act: -0.1700
Data Index: 4396608 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2083. Min Act: -0.1700
Data Index: 6145767 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2083. Min Act: -0.1700
Data Index: 7024786 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2083. Min Act: -0.1700
Data Index: 6443292 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.2083. Min Act: -0.1700
Data Index: 5898365 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1770. Min Act: -0.1700
Data Index: 5965286 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1770. Min Act: -0.1700
Data Index: 6582886 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1770. Min Act: -0.1700
Data Index: 5629290 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1770. Min Act: -0.1700
Data Index: 7216151 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1145. Min Act: -0.1700
Data Index: 8484939 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1458. Min Act: -0.1700
Data Index: 5559056 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1145. Min Act: -0.1700
Data Index: 7806993 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1145. Min Act: -0.1700
Data Index: 7275467 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1145. Min Act: -0.1700
Data Index: 3391788 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3020. Min Range: -5.3020
Max Act: 5.1145. Min Act: -0.1700
Data Index: 7024784 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19