Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5536 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.7175. Min Act: -0.1700
Data Index: 5261840 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.7175. Min Act: -0.1700
Data Index: 4673203 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.6550. Min Act: -0.1700
Data Index: 6936421 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.5300. Min Act: -0.1700
Data Index: 2635256 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.5300. Min Act: -0.1700
Data Index: 1531215 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.4675. Min Act: -0.1700
Data Index: 2000072 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.4050. Min Act: -0.1700
Data Index: 4978176 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.2800. Min Act: -0.1700
Data Index: 1251441 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.3425. Min Act: -0.1700
Data Index: 1124789 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.3425. Min Act: -0.1700
Data Index: 1640918 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.3425. Min Act: -0.1700
Data Index: 8659473 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.2800. Min Act: -0.1700
Data Index: 2129074 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.2800. Min Act: -0.1700
Data Index: 1636914 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.2800. Min Act: -0.1700
Data Index: 8304825 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.2175. Min Act: -0.1700
Data Index: 8781232 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.2175. Min Act: -0.1700
Data Index: 1946875 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.1550. Min Act: -0.1700
Data Index: 3227724 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.1550. Min Act: -0.1700
Data Index: 1342874 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.1550. Min Act: -0.1700
Data Index: 8428076 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7175. Min Range: -9.7175
Max Act: 9.0925. Min Act: -0.1700
Data Index: 4955489 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19