Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5400 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.9507. Min Act: -0.1700
Data Index: 192879 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.7945. Min Act: -0.1700
Data Index: 7990240 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.7320. Min Act: -0.1700
Data Index: 2768123 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.6695. Min Act: -0.1700
Data Index: 146120 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.6695. Min Act: -0.1700
Data Index: 3191474 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.6695. Min Act: -0.1700
Data Index: 5414705 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.6382. Min Act: -0.1700
Data Index: 1774202 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.6070. Min Act: -0.1700
Data Index: 6727529 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.6070. Min Act: -0.1700
Data Index: 8297842 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.5132. Min Act: -0.1700
Data Index: 8592425 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.4820. Min Act: -0.1700
Data Index: 3353836 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.5132. Min Act: -0.1700
Data Index: 6747746 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.4820. Min Act: -0.1700
Data Index: 4472163 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.4507. Min Act: -0.1700
Data Index: 5582745 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.3882. Min Act: -0.1700
Data Index: 6352259 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.4195. Min Act: -0.1700
Data Index: 3241181 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.4195. Min Act: -0.1700
Data Index: 8755305 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.3882. Min Act: -0.1700
Data Index: 2223744 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.3882. Min Act: -0.1700
Data Index: 4290728 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9507. Min Range: -4.9507
Max Act: 4.3570. Min Act: -0.1700
Data Index: 7903735 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19