Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2941 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.2919. Min Act: -0.1699
Data Index: 3370907 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1981. Min Act: -0.1700
Data Index: 8074338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1981. Min Act: -0.1700
Data Index: 811454 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1669. Min Act: -0.1700
Data Index: 8114544 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1356. Min Act: -0.1700
Data Index: 8139027 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1669. Min Act: -0.1699
Data Index: 8196925 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1669. Min Act: -0.1700
Data Index: 4541040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1356. Min Act: -0.1700
Data Index: 6516789 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1697
Data Index: 4115437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 175466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1682
Data Index: 5525820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 4865630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1043. Min Act: -0.1700
Data Index: 141592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 1649792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 8288258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.1043. Min Act: -0.1700
Data Index: 7166890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 4759992 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1698
Data Index: 559168 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 1466962 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2919. Min Range: -4.2919
Max Act: 4.0731. Min Act: -0.1700
Data Index: 321440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19