Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2572. Min Range: -6.2572
Max Act: 6.2572. Min Act: -0.1700
Data Index: 7942853 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2572. Min Range: -6.2572
Max Act: 6.1947. Min Act: -0.1700
Data Index: 7166601 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2572. Min Range: -6.2572
Max Act: 6.0384. Min Act: -0.1700
Data Index: 6507735 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2572. Min Range: -6.2572
Max Act: 6.0072. Min Act: -0.1700
Data Index: 8371884 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.9134. Min Act: -0.1700
Data Index: 6531617 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8822. Min Act: -0.1700
Data Index: 7154214 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8509. Min Act: -0.1700
Data Index: 5823412 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8509. Min Act: -0.1700
Data Index: 294971 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7884. Min Act: -0.1700
Data Index: 7980993 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7884. Min Act: -0.1700
Data Index: 851786 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7884. Min Act: -0.1700
Data Index: 1309841 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7884. Min Act: -0.1700
Data Index: 6399353 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 2563773 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7884. Min Act: -0.1700
Data Index: 1594816 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 7629898 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7259. Min Act: -0.1700
Data Index: 1984387 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 5426353 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7259. Min Act: -0.1700
Data Index: 2930392 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 7726890 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6947. Min Act: -0.1700
Data Index: 418997 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19