Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.7623. Min Act: -0.1700
Data Index: 291210 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.6997. Min Act: -0.1700
Data Index: 291214 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.6058. Min Act: -0.1700
Data Index: 291213 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.5119. Min Act: -0.1700
Data Index: 5209763 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.4806. Min Act: -0.1700
Data Index: 291212 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.4649. Min Act: -0.1700
Data Index: 2255460 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.3238. Min Act: -0.1700
Data Index: 7865679 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.3081. Min Act: -0.1700
Data Index: 2838531 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.2767. Min Act: -0.1700
Data Index: 5519089 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.1981. Min Act: -0.1700
Data Index: 6503727 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.1666. Min Act: -0.1700
Data Index: 873611 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.1037. Min Act: -0.1700
Data Index: 2562728 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.1194. Min Act: -0.1700
Data Index: 1845864 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.1352. Min Act: -0.1700
Data Index: 4479080 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.0879. Min Act: -0.1700
Data Index: 830030 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.0406. Min Act: -0.1700
Data Index: 1951966 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.0563. Min Act: -0.1700
Data Index: 6729118 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.0563. Min Act: -0.1700
Data Index: 3476675 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.0406. Min Act: -0.1700
Data Index: 2584732 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7623. Min Range: -3.7623
Max Act: 3.0406. Min Act: -0.1700
Data Index: 4589711 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19