Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.3391. Min Act: -0.1700
Data Index: 6708329 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.2141. Min Act: -0.1700
Data Index: 5851333 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.0891. Min Act: -0.1700
Data Index: 2722411 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.0891. Min Act: -0.1700
Data Index: 2647892 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.0266. Min Act: -0.1700
Data Index: 2804546 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.0891. Min Act: -0.1700
Data Index: 6998817 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3391. Min Range: -9.3391
Max Act: 9.0266. Min Act: -0.1700
Data Index: 3977700 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.8391. Min Act: -0.1700
Data Index: 6735230 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.8391. Min Act: -0.1700
Data Index: 5037054 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.9016. Min Act: -0.1700
Data Index: 109376 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.9016. Min Act: -0.1700
Data Index: 2837837 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.8391. Min Act: -0.1700
Data Index: 7765237 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.8391. Min Act: -0.1700
Data Index: 7127555 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.7766. Min Act: -0.1700
Data Index: 4646312 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.7141. Min Act: -0.1700
Data Index: 5769143 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.7141. Min Act: -0.1700
Data Index: 6127022 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.7141. Min Act: -0.1700
Data Index: 4778536 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.6516. Min Act: -0.1700
Data Index: 5907192 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.6516. Min Act: -0.1700
Data Index: 7127557 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3391. Min Range: -9.3391
Max Act: 8.6516. Min Act: -0.1700
Data Index: 5491929 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19