Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1029 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.7420. Min Act: -0.1700
Data Index: 3392582 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.6170. Min Act: -0.1700
Data Index: 1893325 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.4920. Min Act: -0.1700
Data Index: 6382584 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.3982. Min Act: -0.1700
Data Index: 5935077 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.4295. Min Act: -0.1700
Data Index: 5382089 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.4295. Min Act: -0.1700
Data Index: 3931143 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.4295. Min Act: -0.1700
Data Index: 3576761 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.3670. Min Act: -0.1700
Data Index: 3846880 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.4295. Min Act: -0.1700
Data Index: 4045317 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.3982. Min Act: -0.1700
Data Index: 6349269 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.3357. Min Act: -0.1700
Data Index: 1397291 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.3045. Min Act: -0.1700
Data Index: 1151535 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2732. Min Act: -0.1700
Data Index: 7114149 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2732. Min Act: -0.1700
Data Index: 7523331 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2420. Min Act: -0.1700
Data Index: 2611570 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2420. Min Act: -0.1700
Data Index: 4906603 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2107. Min Act: -0.1700
Data Index: 4414003 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2107. Min Act: -0.1700
Data Index: 1839684 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2107. Min Act: -0.1700
Data Index: 7209679 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7420. Min Range: -7.7420
Max Act: 7.2420. Min Act: -0.1700
Data Index: 1089945 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19