Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.3973. Min Act: -0.1700
Data Index: 5895355 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.3036. Min Act: -0.1700
Data Index: 1396847 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.2411. Min Act: -0.1700
Data Index: 4391409 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.2411. Min Act: -0.1700
Data Index: 7279845 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.2411. Min Act: -0.1700
Data Index: 5407275 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.2411. Min Act: -0.1700
Data Index: 1298527 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.2098. Min Act: -0.1700
Data Index: 3323965 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.1786. Min Act: -0.1700
Data Index: 2353771 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.1786. Min Act: -0.1700
Data Index: 3814055 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.1161. Min Act: -0.1700
Data Index: 7255824 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.0848. Min Act: -0.1700
Data Index: 5929750 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.0536. Min Act: -0.1700
Data Index: 723352 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.0223. Min Act: -0.1700
Data Index: 8090912 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.0848. Min Act: -0.1700
Data Index: 1909 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.0223. Min Act: -0.1700
Data Index: 595474 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3973. Min Range: -7.3973
Max Act: 6.9911. Min Act: -0.1700
Data Index: 8691078 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3973. Min Range: -7.3973
Max Act: 7.0223. Min Act: -0.1700
Data Index: 1169134 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3973. Min Range: -7.3973
Max Act: 6.9911. Min Act: -0.1700
Data Index: 7164053 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3973. Min Range: -7.3973
Max Act: 6.9598. Min Act: -0.1700
Data Index: 4229843 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3973. Min Range: -7.3973
Max Act: 6.9598. Min Act: -0.1700
Data Index: 4305094 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19