Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.4806. Min Act: -0.1700
Data Index: 3528712 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.3556. Min Act: -0.1700
Data Index: 1260790 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2931. Min Act: -0.1700
Data Index: 6198953 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.3243. Min Act: -0.1700
Data Index: 964602 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.3243. Min Act: -0.1700
Data Index: 7569250 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2931. Min Act: -0.1700
Data Index: 92836 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2931. Min Act: -0.1700
Data Index: 2650037 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2618. Min Act: -0.1700
Data Index: 6312392 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2306. Min Act: -0.1700
Data Index: 3579282 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2618. Min Act: -0.1700
Data Index: 2578321 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2618. Min Act: -0.1700
Data Index: 2046477 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2931. Min Act: -0.1700
Data Index: 2522219 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2618. Min Act: -0.1700
Data Index: 1860588 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2306. Min Act: -0.1700
Data Index: 3859201 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.2306. Min Act: -0.1700
Data Index: 2334286 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.1993. Min Act: -0.1700
Data Index: 4285765 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.1993. Min Act: -0.1700
Data Index: 5307101 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.1681. Min Act: -0.1700
Data Index: 6632205 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.1993. Min Act: -0.1700
Data Index: 184188 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4806. Min Range: -6.4806
Max Act: 6.1993. Min Act: -0.1700
Data Index: 6035293 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19