Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.8872. Min Act: -0.1700
Data Index: 4897016 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.8247. Min Act: -0.1700
Data Index: 6945015 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.7934. Min Act: -0.1700
Data Index: 442971 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.7934. Min Act: -0.1700
Data Index: 2847329 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.6684. Min Act: -0.1700
Data Index: 8117890 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.6372. Min Act: -0.1700
Data Index: 5572800 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.5434. Min Act: -0.1700
Data Index: 5623961 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.5122. Min Act: -0.1700
Data Index: 7842549 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4809. Min Act: -0.1700
Data Index: 5830569 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4809. Min Act: -0.1700
Data Index: 7788194 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4497. Min Act: -0.1700
Data Index: 6039407 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4497. Min Act: -0.1700
Data Index: 7346440 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4184. Min Act: -0.1700
Data Index: 5283236 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4184. Min Act: -0.1700
Data Index: 8696268 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4184. Min Act: -0.1700
Data Index: 7811792 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.4497. Min Act: -0.1700
Data Index: 6026168 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.3559. Min Act: -0.1700
Data Index: 881169 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.3559. Min Act: -0.1700
Data Index: 5620109 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.3872. Min Act: -0.1700
Data Index: 3435101 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8872. Min Range: -6.8872
Max Act: 6.3559. Min Act: -0.1700
Data Index: 6964918 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19