Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.4247. Min Act: -0.1700
Data Index: 1534644 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.3934. Min Act: -0.1700
Data Index: 5752595 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.3309. Min Act: -0.1700
Data Index: 446491 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2997. Min Act: -0.1700
Data Index: 1170027 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2997. Min Act: -0.1700
Data Index: 16272 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2997. Min Act: -0.1700
Data Index: 8786049 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2997. Min Act: -0.1700
Data Index: 7018610 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2684. Min Act: -0.1700
Data Index: 5752581 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2372. Min Act: -0.1700
Data Index: 4370298 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2059. Min Act: -0.1699
Data Index: 4476322 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2059. Min Act: -0.1700
Data Index: 559075 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2059. Min Act: -0.1700
Data Index: 3727215 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2059. Min Act: -0.1700
Data Index: 3715215 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2372. Min Act: -0.1700
Data Index: 2038629 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2059. Min Act: -0.1700
Data Index: 3255090 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.2059. Min Act: -0.1700
Data Index: 5752580 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.1747. Min Act: -0.1700
Data Index: 5752583 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.1747. Min Act: -0.1700
Data Index: 4400222 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.1747. Min Act: -0.1700
Data Index: 2592572 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4247. Min Range: -5.4247
Max Act: 5.1747. Min Act: -0.1700
Data Index: 898386 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19