Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.7846. Min Act: -0.1700
Data Index: 1057280 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.6283. Min Act: -0.1700
Data Index: 6832736 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.5658. Min Act: -0.1700
Data Index: 2447678 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.5346. Min Act: -0.1700
Data Index: 8163610 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.5346. Min Act: -0.1700
Data Index: 3149501 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.4721. Min Act: -0.1700
Data Index: 7200920 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.5346. Min Act: -0.1700
Data Index: 683709 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.4721. Min Act: -0.1700
Data Index: 261229 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3783. Min Act: -0.1700
Data Index: 7779829 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3783. Min Act: -0.1700
Data Index: 1197855 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3783. Min Act: -0.1700
Data Index: 6922109 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3471. Min Act: -0.1700
Data Index: 4445316 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3783. Min Act: -0.1700
Data Index: 524881 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3471. Min Act: -0.1700
Data Index: 6802690 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3471. Min Act: -0.1700
Data Index: 3630973 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3471. Min Act: -0.1700
Data Index: 2840059 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3158. Min Act: -0.1700
Data Index: 6732689 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3158. Min Act: -0.1700
Data Index: 244153 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.3158. Min Act: -0.1700
Data Index: 147908 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7846. Min Range: -6.7846
Max Act: 6.2846. Min Act: -0.1700
Data Index: 1853112 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19