Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1439 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.6280. Min Act: -0.1700
Data Index: 331862 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.5655. Min Act: -0.1700
Data Index: 2640692 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.5030. Min Act: -0.1700
Data Index: 4081547 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.4405. Min Act: -0.1700
Data Index: 6607054 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.4092. Min Act: -0.1700
Data Index: 3173717 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.4092. Min Act: -0.1700
Data Index: 6201738 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.4092. Min Act: -0.1700
Data Index: 3858750 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3467. Min Act: -0.1700
Data Index: 6770920 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3467. Min Act: -0.1700
Data Index: 4383374 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3467. Min Act: -0.1700
Data Index: 3129241 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3780. Min Act: -0.1700
Data Index: 6771983 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3467. Min Act: -0.1700
Data Index: 4321238 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3467. Min Act: -0.1700
Data Index: 798403 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.3155. Min Act: -0.1700
Data Index: 4323266 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.2530. Min Act: -0.1700
Data Index: 7861833 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.2842. Min Act: -0.1700
Data Index: 1916234 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.2842. Min Act: -0.1700
Data Index: 6010281 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.2842. Min Act: -0.1700
Data Index: 5367789 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.2530. Min Act: -0.1700
Data Index: 125382 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6280. Min Range: -4.6280
Max Act: 4.2530. Min Act: -0.1700
Data Index: 1918808 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19