Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.7825. Min Act: -0.1700
Data Index: 5867303 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.8138. Min Act: -0.1700
Data Index: 6332322 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.6888. Min Act: -0.1700
Data Index: 897058 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.5325. Min Act: -0.1700
Data Index: 2283361 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4388. Min Act: -0.1700
Data Index: 7560750 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4388. Min Act: -0.1700
Data Index: 3786774 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4388. Min Act: -0.1700
Data Index: 4849050 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4075. Min Act: -0.1700
Data Index: 5258338 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4075. Min Act: -0.1700
Data Index: 455308 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4075. Min Act: -0.1700
Data Index: 3018282 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4075. Min Act: -0.1700
Data Index: 4600686 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.4075. Min Act: -0.1700
Data Index: 4146395 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3763. Min Act: -0.1700
Data Index: 7474808 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3763. Min Act: -0.1700
Data Index: 3535426 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3450. Min Act: -0.1700
Data Index: 1391005 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3450. Min Act: -0.1700
Data Index: 2914300 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3450. Min Act: -0.1700
Data Index: 1712561 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3450. Min Act: -0.1700
Data Index: 7813303 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3450. Min Act: -0.1700
Data Index: 8266822 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8138. Min Range: -4.8138
Max Act: 4.3450. Min Act: -0.1700
Data Index: 5350535 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19