Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2320 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.7338. Min Act: -0.1700
Data Index: 3621320 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.6401. Min Act: -0.1700
Data Index: 8336930 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.5151. Min Act: -0.1700
Data Index: 2225521 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.4213. Min Act: -0.1700
Data Index: 2417894 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.3588. Min Act: -0.1700
Data Index: 7739847 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.2338. Min Act: -0.1700
Data Index: 822324 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.2338. Min Act: -0.1700
Data Index: 5109755 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.2026. Min Act: -0.1700
Data Index: 726879 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.2026. Min Act: -0.1700
Data Index: 8661335 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.1713. Min Act: -0.1700
Data Index: 2920320 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.1401. Min Act: -0.1700
Data Index: 2054872 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.1088. Min Act: -0.1700
Data Index: 6872113 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.0776. Min Act: -0.1700
Data Index: 4686958 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.1088. Min Act: -0.1700
Data Index: 8435399 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.0463. Min Act: -0.1700
Data Index: 4845533 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.0463. Min Act: -0.1700
Data Index: 845198 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.0151. Min Act: -0.1700
Data Index: 5089048 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.0151. Min Act: -0.1700
Data Index: 6851595 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7338. Min Range: -6.7338
Max Act: 6.0151. Min Act: -0.1700
Data Index: 5470160 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7338. Min Range: -6.7338
Max Act: 5.9838. Min Act: -0.1700
Data Index: 3967943 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19