Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.4708. Min Act: -0.1699
Data Index: 596089 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.4004. Min Act: -0.1695
Data Index: 8798493 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.4180. Min Act: -0.1698
Data Index: 6201802 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.4004. Min Act: -0.1700
Data Index: 3927643 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.4180. Min Act: -0.1695
Data Index: 5864478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3475. Min Act: -0.1685
Data Index: 8044672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3475. Min Act: -0.1627
Data Index: 6278099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3652. Min Act: -0.1697
Data Index: 2990652 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3475. Min Act: -0.1699
Data Index: 3040216 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3475. Min Act: -0.1700
Data Index: 8315354 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3652. Min Act: -0.1698
Data Index: 45884 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3299. Min Act: -0.1693
Data Index: 5099563 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2946. Min Act: -0.1691
Data Index: 8457012 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2946. Min Act: -0.1698
Data Index: 7079792 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.3123. Min Act: -0.1700
Data Index: 6591329 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2946. Min Act: -0.1700
Data Index: 4198250 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2946. Min Act: -0.1555
Data Index: 2418256 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2946. Min Act: -0.1700
Data Index: 5218618 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2770. Min Act: -0.1700
Data Index: 966659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4708. Min Range: -1.4708
Max Act: 1.2770. Min Act: -0.1697
Data Index: 1932273 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19