Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3934. Min Range: -8.3934
Max Act: 8.3934. Min Act: -0.1700
Data Index: 3391086 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.7059. Min Act: -0.1700
Data Index: 4005922 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.4872. Min Act: -0.1700
Data Index: 2330659 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.3934. Min Act: -0.1700
Data Index: 2276094 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.2372. Min Act: -0.1700
Data Index: 1107706 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.2997. Min Act: -0.1700
Data Index: 1380154 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.2372. Min Act: -0.1700
Data Index: 6754303 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.1122. Min Act: -0.1700
Data Index: 8040643 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.1747. Min Act: -0.1700
Data Index: 6142470 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.0809. Min Act: -0.1700
Data Index: 599052 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.0497. Min Act: -0.1700
Data Index: 2379586 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.0497. Min Act: -0.1700
Data Index: 3652476 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.9872. Min Act: -0.1700
Data Index: 6484595 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3934. Min Range: -8.3934
Max Act: 7.0497. Min Act: -0.1700
Data Index: 2764121 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.9559. Min Act: -0.1700
Data Index: 1540128 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.9559. Min Act: -0.1700
Data Index: 7237415 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.8934. Min Act: -0.1700
Data Index: 5317022 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.8622. Min Act: -0.1700
Data Index: 4109860 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.9559. Min Act: -0.1700
Data Index: 77736 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3934. Min Range: -8.3934
Max Act: 6.8934. Min Act: -0.1700
Data Index: 3109658 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19