Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 883 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.9125. Min Act: -0.1700
Data Index: 1163960 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7093. Min Act: -0.1700
Data Index: 6738175 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.7093. Min Act: -0.1700
Data Index: 772933 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6780. Min Act: -0.1700
Data Index: 8493000 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6623. Min Act: -0.1700
Data Index: 7731493 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6467. Min Act: -0.1700
Data Index: 8684753 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6623. Min Act: -0.1700
Data Index: 1078250 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6154. Min Act: -0.1700
Data Index: 5504140 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6154. Min Act: -0.1700
Data Index: 4592246 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.6154. Min Act: -0.1700
Data Index: 2165309 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5841. Min Act: -0.1700
Data Index: 240351 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5684. Min Act: -0.1700
Data Index: 4755263 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5528. Min Act: -0.1700
Data Index: 3674340 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5371. Min Act: -0.1700
Data Index: 6366637 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5528. Min Act: -0.1700
Data Index: 6526864 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5371. Min Act: -0.1700
Data Index: 4115606 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5371. Min Act: -0.1700
Data Index: 4659534 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5371. Min Act: -0.1700
Data Index: 8511648 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5058. Min Act: -0.1700
Data Index: 7366323 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9125. Min Range: -3.9125
Max Act: 3.5058. Min Act: -0.1700
Data Index: 2262962 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19