Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0881. Min Range: -5.0881
Max Act: 5.0881. Min Act: -0.1700
Data Index: 6557841 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0881. Min Range: -5.0881
Max Act: 5.0568. Min Act: -0.1700
Data Index: 7577746 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0881. Min Range: -5.0881
Max Act: 5.0256. Min Act: -0.1700
Data Index: 3885175 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9943. Min Act: -0.1700
Data Index: 2731953 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0881. Min Range: -5.0881
Max Act: 5.0256. Min Act: -0.1700
Data Index: 5503715 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9631. Min Act: -0.1700
Data Index: 7981444 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9631. Min Act: -0.1700
Data Index: 3603898 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9318. Min Act: -0.1700
Data Index: 661933 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9006. Min Act: -0.1700
Data Index: 8620325 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9006. Min Act: -0.1700
Data Index: 661939 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9006. Min Act: -0.1700
Data Index: 4508391 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9318. Min Act: -0.1700
Data Index: 6066505 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9631. Min Act: -0.1700
Data Index: 6055418 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.8068. Min Act: -0.1700
Data Index: 2074523 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.8381. Min Act: -0.1700
Data Index: 661942 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.8381. Min Act: -0.1700
Data Index: 2731949 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9006. Min Act: -0.1700
Data Index: 7093584 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.8693. Min Act: -0.1700
Data Index: 4553446 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.9006. Min Act: -0.1700
Data Index: 5503720 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0881. Min Range: -5.0881
Max Act: 4.8693. Min Act: -0.1700
Data Index: 7556085 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19