Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.5607. Min Act: -0.1700
Data Index: 6861591 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.5764. Min Act: -0.1700
Data Index: 7903297 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.5451. Min Act: -0.1700
Data Index: 678896 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.5138. Min Act: -0.1700
Data Index: 6805510 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4824. Min Act: -0.1700
Data Index: 4869642 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4824. Min Act: -0.1700
Data Index: 2482028 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4668. Min Act: -0.1700
Data Index: 8282904 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4668. Min Act: -0.1700
Data Index: 7903299 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4041. Min Act: -0.1700
Data Index: 6587145 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4041. Min Act: -0.1700
Data Index: 413551 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.4041. Min Act: -0.1700
Data Index: 856176 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3570. Min Act: -0.1700
Data Index: 5356915 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3884. Min Act: -0.1700
Data Index: 3681698 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3413. Min Act: -0.1700
Data Index: 7665361 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3727. Min Act: -0.1700
Data Index: 8708882 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3570. Min Act: -0.1700
Data Index: 2815380 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3257. Min Act: -0.1700
Data Index: 2114505 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3413. Min Act: -0.1700
Data Index: 7942753 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3257. Min Act: -0.1700
Data Index: 7619680 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5764. Min Range: -3.5764
Max Act: 3.3413. Min Act: -0.1700
Data Index: 1970964 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19