Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9989. Min Act: -0.1700
Data Index: 780562 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9364. Min Act: -0.1700
Data Index: 1638879 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8739. Min Act: -0.1700
Data Index: 3502096 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9052. Min Act: -0.1700
Data Index: 5633088 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.9052. Min Act: -0.1700
Data Index: 6060996 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8739. Min Act: -0.1700
Data Index: 1638878 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8739. Min Act: -0.1700
Data Index: 5633089 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8426. Min Act: -0.1700
Data Index: 7487214 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8270. Min Act: -0.1700
Data Index: 3500630 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8426. Min Act: -0.1700
Data Index: 1266484 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8113. Min Act: -0.1700
Data Index: 4496511 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.8270. Min Act: -0.1700
Data Index: 1235552 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7801. Min Act: -0.1700
Data Index: 2890527 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7957. Min Act: -0.1700
Data Index: 5501510 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7801. Min Act: -0.1700
Data Index: 3870187 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7488. Min Act: -0.1700
Data Index: 3576774 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7332. Min Act: -0.1700
Data Index: 8551676 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7019. Min Act: -0.1700
Data Index: 6948817 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.7019. Min Act: -0.1700
Data Index: 5633086 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9989. Min Range: -3.9989
Max Act: 3.6862. Min Act: -0.1700
Data Index: 4727702 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19