Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2226. Min Range: -5.2226
Max Act: 5.2226. Min Act: -0.1700
Data Index: 5517010 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2226. Min Range: -5.2226
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5517011 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2226. Min Range: -5.2226
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5517026 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2226. Min Range: -5.2226
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5517025 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.9726. Min Act: -0.1700
Data Index: 2507201 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.9101. Min Act: -0.1700
Data Index: 5206722 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8476. Min Act: -0.1700
Data Index: 1486521 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8476. Min Act: -0.1700
Data Index: 82386 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8476. Min Act: -0.1700
Data Index: 5332877 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8476. Min Act: -0.1700
Data Index: 5769388 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8476. Min Act: -0.1700
Data Index: 7125153 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.7851. Min Act: -0.1700
Data Index: 4235515 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 5053833 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 77532 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8476. Min Act: -0.1700
Data Index: 2574000 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 6747521 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 6891307 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 110056 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 5398040 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2226. Min Range: -5.2226
Max Act: 4.8163. Min Act: -0.1700
Data Index: 7310065 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19