Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.8422. Min Act: -0.1700
Data Index: 3366287 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.6860. Min Act: -0.1700
Data Index: 6219934 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.5297. Min Act: -0.1700
Data Index: 1013580 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.4672. Min Act: -0.1700
Data Index: 6682303 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.4672. Min Act: -0.1700
Data Index: 289441 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.3422. Min Act: -0.1700
Data Index: 4470375 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.3422. Min Act: -0.1700
Data Index: 8486054 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.3422. Min Act: -0.1700
Data Index: 6384288 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.2797. Min Act: -0.1700
Data Index: 97165 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.2797. Min Act: -0.1700
Data Index: 3019957 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.2485. Min Act: -0.1700
Data Index: 937607 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.2172. Min Act: -0.1700
Data Index: 7003801 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.1860. Min Act: -0.1700
Data Index: 1163850 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.2172. Min Act: -0.1700
Data Index: 568223 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.1860. Min Act: -0.1700
Data Index: 1525034 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.1547. Min Act: -0.1700
Data Index: 4802143 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.1547. Min Act: -0.1700
Data Index: 5632713 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.0297. Min Act: -0.1700
Data Index: 352662 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.0297. Min Act: -0.1700
Data Index: 2536625 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8422. Min Range: -7.8422
Max Act: 7.0610. Min Act: -0.1700
Data Index: 4661212 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19