Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.4163. Min Act: -0.1700
Data Index: 7300363 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.2913. Min Act: -0.1700
Data Index: 3920243 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.2913. Min Act: -0.1700
Data Index: 1815928 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.2288. Min Act: -0.1700
Data Index: 7801892 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1976. Min Act: -0.1700
Data Index: 8452608 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1976. Min Act: -0.1700
Data Index: 4933068 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1663. Min Act: -0.1700
Data Index: 974493 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1663. Min Act: -0.1700
Data Index: 1867880 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1038. Min Act: -0.1700
Data Index: 8455047 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 8397739 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 635472 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 794993 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 6906300 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4163. Min Range: -6.4163
Max Act: 5.9788. Min Act: -0.1700
Data Index: 8643971 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0101. Min Act: -0.1700
Data Index: 8317173 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4163. Min Range: -6.4163
Max Act: 5.9476. Min Act: -0.1700
Data Index: 5177330 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4163. Min Range: -6.4163
Max Act: 5.9476. Min Act: -0.1700
Data Index: 207733 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4163. Min Range: -6.4163
Max Act: 5.9476. Min Act: -0.1700
Data Index: 992718 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4163. Min Range: -6.4163
Max Act: 5.9476. Min Act: -0.1700
Data Index: 36154 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4163. Min Range: -6.4163
Max Act: 5.9476. Min Act: -0.1700
Data Index: 3304312 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19