Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.4390. Min Act: -0.1700
Data Index: 7907462 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7827. Min Range: -7.7827
Max Act: 7.5952. Min Act: -0.1700
Data Index: 2878354 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7827. Min Range: -7.7827
Max Act: 5.4702. Min Act: -0.1700
Data Index: 2477011 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7827. Min Range: -7.7827
Max Act: 7.4077. Min Act: -0.1700
Data Index: 6462443 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.7515. Min Act: -0.1700
Data Index: 1209705 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7827. Min Range: -7.7827
Max Act: 7.2827. Min Act: -0.1700
Data Index: 4219587 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7827. Min Range: -7.7827
Max Act: 5.2202. Min Act: -0.1700
Data Index: 369059 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7827. Min Range: -7.7827
Max Act: 7.7827. Min Act: -0.1700
Data Index: 21051 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.2515. Min Act: -0.1700
Data Index: 8459307 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.9702. Min Act: -0.1700
Data Index: 7649302 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.3140. Min Act: -0.1700
Data Index: 6437409 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7827. Min Range: -7.7827
Max Act: 3.7825. Min Act: -0.1700
Data Index: 4973279 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7827. Min Range: -7.7827
Max Act: 7.0015. Min Act: -0.1700
Data Index: 433053 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.0952. Min Act: -0.1700
Data Index: 6047977 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7827. Min Range: -7.7827
Max Act: 7.0327. Min Act: -0.1700
Data Index: 3566656 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.8452. Min Act: -0.1700
Data Index: 3005722 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.7827. Min Act: -0.1700
Data Index: 5588402 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.8140. Min Act: -0.1700
Data Index: 598735 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7827. Min Range: -7.7827
Max Act: 3.8764. Min Act: -0.1700
Data Index: 2556447 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7827. Min Range: -7.7827
Max Act: 6.7515. Min Act: -0.1700
Data Index: 5653590 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19