Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.8344. Min Act: -0.1700
Data Index: 351108 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.8031. Min Act: -0.1700
Data Index: 7482915 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.7406. Min Act: -0.1700
Data Index: 6237639 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.7406. Min Act: -0.1700
Data Index: 5510308 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.7093. Min Act: -0.1700
Data Index: 4302830 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6780. Min Act: -0.1700
Data Index: 3786115 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6624. Min Act: -0.1700
Data Index: 858105 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6624. Min Act: -0.1700
Data Index: 1845909 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6780. Min Act: -0.1700
Data Index: 2665311 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6624. Min Act: -0.1700
Data Index: 2684460 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6311. Min Act: -0.1700
Data Index: 1832911 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 4554711 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 2327202 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 3966195 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6467. Min Act: -0.1700
Data Index: 5773479 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6311. Min Act: -0.1700
Data Index: 3025244 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.6154. Min Act: -0.1700
Data Index: 5814458 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5998. Min Act: -0.1700
Data Index: 3101428 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5998. Min Act: -0.1700
Data Index: 8631960 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8344. Min Range: -3.8344
Max Act: 3.5841. Min Act: -0.1700
Data Index: 2048218 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19