Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4169 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.4651. Min Act: -0.1700
Data Index: 7460063 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.2776. Min Act: -0.1700
Data Index: 1626971 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.2776. Min Act: -0.1700
Data Index: 4817202 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 3978291 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 2850606 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 1110675 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 3249445 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 3888270 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0901. Min Act: -0.1700
Data Index: 6287439 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 2595046 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 6348192 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 8492478 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 8107309 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 21378 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4651. Min Range: -8.4651
Max Act: 8.0276. Min Act: -0.1700
Data Index: 1811218 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4651. Min Range: -8.4651
Max Act: 7.9026. Min Act: -0.1700
Data Index: 2781082 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4651. Min Range: -8.4651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 1297393 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4651. Min Range: -8.4651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 5783069 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4651. Min Range: -8.4651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 3981575 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4651. Min Range: -8.4651
Max Act: 7.9651. Min Act: -0.1700
Data Index: 6353876 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19