Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.9812. Min Act: -0.1700
Data Index: 8042023 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.8562. Min Act: -0.1700
Data Index: 1765347 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.7624. Min Act: -0.1700
Data Index: 2900928 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.7624. Min Act: -0.1700
Data Index: 3315278 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.7624. Min Act: -0.1700
Data Index: 3561204 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.7312. Min Act: -0.1700
Data Index: 2516021 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.7312. Min Act: -0.1700
Data Index: 8786605 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6999. Min Act: -0.1700
Data Index: 1752680 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6374. Min Act: -0.1700
Data Index: 8611402 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6687. Min Act: -0.1700
Data Index: 6468412 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6374. Min Act: -0.1700
Data Index: 732521 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 4466201 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6374. Min Act: -0.1700
Data Index: 3874598 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6687. Min Act: -0.1700
Data Index: 7436236 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6374. Min Act: -0.1700
Data Index: 7101544 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 1483674 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 1307677 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 7902033 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 8200044 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9812. Min Range: -5.9812
Max Act: 5.6062. Min Act: -0.1700
Data Index: 944422 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19