Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.4840. Min Act: -0.1700
Data Index: 4040801 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.4215. Min Act: -0.1700
Data Index: 1483836 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.4215. Min Act: -0.1700
Data Index: 8174732 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.2340. Min Act: -0.1700
Data Index: 2452804 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4840. Min Range: -9.4840
Max Act: 9.1715. Min Act: -0.1700
Data Index: 2837374 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.9840. Min Act: -0.1700
Data Index: 3046475 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.9840. Min Act: -0.1700
Data Index: 4414147 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.9840. Min Act: -0.1700
Data Index: 5271807 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.9215. Min Act: -0.1700
Data Index: 6630923 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7965. Min Act: -0.1700
Data Index: 8125819 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7965. Min Act: -0.1700
Data Index: 1310097 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7340. Min Act: -0.1700
Data Index: 694063 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.7340. Min Act: -0.1700
Data Index: 1264878 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.6715. Min Act: -0.1700
Data Index: 1209974 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.6090. Min Act: -0.1700
Data Index: 1998215 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.6090. Min Act: -0.1700
Data Index: 5302420 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.4840. Min Act: -0.1700
Data Index: 5289370 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.5152. Min Act: -0.1700
Data Index: 5671352 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.4215. Min Act: -0.1700
Data Index: 5905805 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4840. Min Range: -9.4840
Max Act: 8.3902. Min Act: -0.1700
Data Index: 8110056 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19