Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 7293127 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.5197. Min Act: -0.1700
Data Index: 3283420 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.4260. Min Act: -0.1700
Data Index: 8066854 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.4260. Min Act: -0.1700
Data Index: 2857984 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2697. Min Act: -0.1700
Data Index: 3283419 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2697. Min Act: -0.1700
Data Index: 1942943 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2697. Min Act: -0.1700
Data Index: 3599114 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2385. Min Act: -0.1700
Data Index: 4117293 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2385. Min Act: -0.1700
Data Index: 951343 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7835102 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5026862 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2385. Min Act: -0.1700
Data Index: 350504 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7978693 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1760. Min Act: -0.1700
Data Index: 1069963 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1447. Min Act: -0.1700
Data Index: 6342679 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1135. Min Act: -0.1700
Data Index: 2166387 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0822. Min Act: -0.1700
Data Index: 1003961 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0822. Min Act: -0.1700
Data Index: 4809490 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0822. Min Act: -0.1700
Data Index: 348031 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0822. Min Act: -0.1700
Data Index: 5039195 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19