Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.4712. Min Act: -0.1700
Data Index: 7139821 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.4712. Min Act: -0.1700
Data Index: 8755750 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.3462. Min Act: -0.1700
Data Index: 4560478 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.3462. Min Act: -0.1700
Data Index: 8479146 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.3150. Min Act: -0.1700
Data Index: 3813218 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.3150. Min Act: -0.1700
Data Index: 4669287 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.3150. Min Act: -0.1700
Data Index: 6488370 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.2212. Min Act: -0.1700
Data Index: 2348062 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.2525. Min Act: -0.1700
Data Index: 5961543 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.1587. Min Act: -0.1700
Data Index: 3789896 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.1587. Min Act: -0.1700
Data Index: 7275038 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.1587. Min Act: -0.1700
Data Index: 939056 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0650. Min Act: -0.1700
Data Index: 3784489 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0962. Min Act: -0.1700
Data Index: 938859 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0025. Min Act: -0.1700
Data Index: 880314 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0337. Min Act: -0.1700
Data Index: 1727166 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0337. Min Act: -0.1700
Data Index: 3598253 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0025. Min Act: -0.1700
Data Index: 1108144 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0025. Min Act: -0.1700
Data Index: 3878780 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4712. Min Range: -7.4712
Max Act: 7.0025. Min Act: -0.1700
Data Index: 3269702 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19