Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.6494. Min Act: -0.1700
Data Index: 8558988 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.5555. Min Act: -0.1700
Data Index: 1406084 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.4929. Min Act: -0.1700
Data Index: 790652 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.4146. Min Act: -0.1700
Data Index: 269132 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3989. Min Act: -0.1700
Data Index: 3062145 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3518. Min Act: -0.1700
Data Index: 3952292 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3675. Min Act: -0.1700
Data Index: 1176581 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3675. Min Act: -0.1700
Data Index: 4465501 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3675. Min Act: -0.1700
Data Index: 3395981 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3361. Min Act: -0.1700
Data Index: 300809 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3518. Min Act: -0.1700
Data Index: 8700091 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3048. Min Act: -0.1700
Data Index: 1312862 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.2891. Min Act: -0.1700
Data Index: 2738915 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.2733. Min Act: -0.1700
Data Index: 2037306 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3048. Min Act: -0.1700
Data Index: 7725682 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3048. Min Act: -0.1700
Data Index: 2108479 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.2891. Min Act: -0.1700
Data Index: 3557223 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.3048. Min Act: -0.1700
Data Index: 3470191 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.2733. Min Act: -0.1700
Data Index: 5504109 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6494. Min Range: -3.6494
Max Act: 3.2891. Min Act: -0.1700
Data Index: 5955263 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19