Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5950 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1869. Min Act: -0.1700
Data Index: 5738025 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.1244. Min Act: -0.1700
Data Index: 8013845 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0931. Min Act: -0.1700
Data Index: 2560343 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0931. Min Act: -0.1700
Data Index: 4594327 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0931. Min Act: -0.1700
Data Index: 5950524 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0618. Min Act: -0.1700
Data Index: 7075955 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0618. Min Act: -0.1700
Data Index: 2235701 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0618. Min Act: -0.1700
Data Index: 2286197 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0618. Min Act: -0.1700
Data Index: 4569053 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 3563756 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9993. Min Act: -0.1700
Data Index: 3992517 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5515388 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 55157 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1982977 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 2032637 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9993. Min Act: -0.1700
Data Index: 3004572 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9993. Min Act: -0.1700
Data Index: 7094247 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9993. Min Act: -0.1700
Data Index: 5650407 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1869. Min Range: -4.1869
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5402999 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1869. Min Range: -4.1869
Max Act: 3.9993. Min Act: -0.1700
Data Index: 5331028 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19