Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2952. Min Range: -4.2952
Max Act: 4.2952. Min Act: -0.1700
Data Index: 1350813 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.9514. Min Act: -0.1700
Data Index: 917205 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8576. Min Act: -0.1700
Data Index: 2028956 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8889. Min Act: -0.1700
Data Index: 5401367 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8420. Min Act: -0.1700
Data Index: 5135314 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8263. Min Act: -0.1700
Data Index: 5935636 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8263. Min Act: -0.1700
Data Index: 7434843 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8263. Min Act: -0.1700
Data Index: 1423670 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7794. Min Act: -0.1700
Data Index: 7364752 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7951. Min Act: -0.1700
Data Index: 6746936 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7794. Min Act: -0.1700
Data Index: 2748417 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.8107. Min Act: -0.1700
Data Index: 5652716 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7794. Min Act: -0.1700
Data Index: 2734641 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7794. Min Act: -0.1700
Data Index: 6768722 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7638. Min Act: -0.1700
Data Index: 4434497 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7638. Min Act: -0.1700
Data Index: 7806283 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7794. Min Act: -0.1700
Data Index: 6036376 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7482. Min Act: -0.1700
Data Index: 8798842 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7482. Min Act: -0.1700
Data Index: 4759314 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2952. Min Range: -4.2952
Max Act: 3.7794. Min Act: -0.1700
Data Index: 2786122 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19