Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.5671. Min Act: -0.1700
Data Index: 4750802 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.4794. Min Act: -0.1700
Data Index: 1633223 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.4443. Min Act: -0.1700
Data Index: 6454494 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.4267. Min Act: -0.1700
Data Index: 7799049 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.4267. Min Act: -0.1700
Data Index: 6543052 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.3914. Min Act: -0.1700
Data Index: 2088823 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.3385. Min Act: -0.1700
Data Index: 1970475 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.3209. Min Act: -0.1700
Data Index: 260501 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.3209. Min Act: -0.1700
Data Index: 4194659 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2856. Min Act: -0.1700
Data Index: 42184 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2503. Min Act: -0.1700
Data Index: 7176593 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2680. Min Act: -0.1700
Data Index: 4824954 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2856. Min Act: -0.1700
Data Index: 160345 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2327. Min Act: -0.1700
Data Index: 7305521 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2503. Min Act: -0.1700
Data Index: 5481213 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2327. Min Act: -0.1700
Data Index: 5432023 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2327. Min Act: -0.1700
Data Index: 1799828 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2327. Min Act: -0.1700
Data Index: 7511798 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2327. Min Act: -0.1700
Data Index: 2576040 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5671. Min Range: -1.5671
Max Act: 1.2151. Min Act: -0.1700
Data Index: 3841460 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19