Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.5717. Min Act: -0.1700
Data Index: 7931676 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.5092. Min Act: -0.1700
Data Index: 8796769 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4779. Min Act: -0.1700
Data Index: 8746476 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4467. Min Act: -0.1700
Data Index: 8436607 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4779. Min Act: -0.1700
Data Index: 7086126 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4467. Min Act: -0.1700
Data Index: 8481191 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4467. Min Act: -0.1700
Data Index: 3668166 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 7200367 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 7440984 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 4774752 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 3594298 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 2698198 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 2649648 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 1151613 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.3529. Min Act: -0.1700
Data Index: 569838 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.4154. Min Act: -0.1700
Data Index: 551450 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.3529. Min Act: -0.1700
Data Index: 2233954 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.3842. Min Act: -0.1700
Data Index: 5279498 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.3842. Min Act: -0.1700
Data Index: 4270110 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5717. Min Range: -4.5717
Max Act: 4.3842. Min Act: -0.1700
Data Index: 4639360 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19