Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.8457. Min Act: -0.1700
Data Index: 2485476 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.7519. Min Act: -0.1700
Data Index: 4927442 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.7207. Min Act: -0.1700
Data Index: 3600689 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.7207. Min Act: -0.1700
Data Index: 3780235 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.6582. Min Act: -0.1700
Data Index: 560071 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.6269. Min Act: -0.1700
Data Index: 6462600 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.5957. Min Act: -0.1700
Data Index: 7444958 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.6269. Min Act: -0.1700
Data Index: 5508196 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.5644. Min Act: -0.1700
Data Index: 3450366 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.5644. Min Act: -0.1700
Data Index: 4691679 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.5644. Min Act: -0.1700
Data Index: 5374209 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.5644. Min Act: -0.1700
Data Index: 689519 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.5019. Min Act: -0.1700
Data Index: 7633393 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4707. Min Act: -0.1700
Data Index: 3450367 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4707. Min Act: -0.1700
Data Index: 243085 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4707. Min Act: -0.1700
Data Index: 8126825 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4707. Min Act: -0.1700
Data Index: 3574823 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4707. Min Act: -0.1700
Data Index: 4891135 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4707. Min Act: -0.1700
Data Index: 4691677 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8457. Min Range: -7.8457
Max Act: 7.4394. Min Act: -0.1700
Data Index: 747572 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19