Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.8271. Min Act: -0.1700
Data Index: 6122608 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.4521. Min Act: -0.1700
Data Index: 3150246 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.4208. Min Act: -0.1700
Data Index: 4078392 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2958. Min Act: -0.1700
Data Index: 7709703 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4039221 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 816641 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2958. Min Act: -0.1700
Data Index: 129118 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4931831 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2958. Min Act: -0.1700
Data Index: 810985 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2958. Min Act: -0.1700
Data Index: 6911061 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 7196007 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 7029688 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 4640586 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 553161 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 4490943 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2333. Min Act: -0.1700
Data Index: 6859079 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2646. Min Act: -0.1700
Data Index: 7819478 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2333. Min Act: -0.1700
Data Index: 5623895 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2333. Min Act: -0.1700
Data Index: 5578747 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8271. Min Range: -5.8271
Max Act: 5.2333. Min Act: -0.1700
Data Index: 4777799 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19