Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5569 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6110688 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.3065. Min Act: -0.1700
Data Index: 5914165 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 3079228 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2753. Min Act: -0.1700
Data Index: 1802965 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 5119117 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 7863345 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2128. Min Act: -0.1700
Data Index: 6629467 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 4767759 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 2791814 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 3232807 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 2715427 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1503. Min Act: -0.1700
Data Index: 4697865 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1503. Min Act: -0.1700
Data Index: 5904639 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1503. Min Act: -0.1700
Data Index: 5049352 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1503. Min Act: -0.1700
Data Index: 4622662 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1190. Min Act: -0.1700
Data Index: 4648816 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1190. Min Act: -0.1700
Data Index: 2621427 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1190. Min Act: -0.1700
Data Index: 1176083 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1503. Min Act: -0.1700
Data Index: 2112778 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1190. Min Act: -0.1700
Data Index: 4938820 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19