Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.8631. Min Act: -0.1700
Data Index: 6437436 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.8631. Min Act: -0.1700
Data Index: 3747616 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.8318. Min Act: -0.1700
Data Index: 1220327 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.8006. Min Act: -0.1700
Data Index: 7599068 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.8006. Min Act: -0.1700
Data Index: 1600093 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.7693. Min Act: -0.1700
Data Index: 4835086 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.7381. Min Act: -0.1700
Data Index: 3126960 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.7381. Min Act: -0.1700
Data Index: 8244288 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6756. Min Act: -0.1700
Data Index: 1446210 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 7858968 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 6985490 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 21077 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 436726 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 8542561 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.6131. Min Act: -0.1700
Data Index: 321437 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.5818. Min Act: -0.1700
Data Index: 4378067 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.5818. Min Act: -0.1700
Data Index: 4442754 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.5818. Min Act: -0.1700
Data Index: 4706915 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 7394752 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8631. Min Range: -6.8631
Max Act: 6.5506. Min Act: -0.1700
Data Index: 3314353 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19