Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1942 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4728. Min Range: -8.4728
Max Act: 8.4728. Min Act: -0.1700
Data Index: 2926648 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4728. Min Range: -8.4728
Max Act: 8.0353. Min Act: -0.1700
Data Index: 7140859 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4728. Min Range: -8.4728
Max Act: 8.0353. Min Act: -0.1700
Data Index: 5582216 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.9728. Min Act: -0.1700
Data Index: 4500576 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.4103. Min Act: -0.1700
Data Index: 5070386 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.3165. Min Act: -0.1699
Data Index: 8137781 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 3856158 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.3165. Min Act: -0.1700
Data Index: 1750002 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.2853. Min Act: -0.1700
Data Index: 6814848 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.1915. Min Act: -0.1700
Data Index: 4516411 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 4539402 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 555870 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.0978. Min Act: -0.1700
Data Index: 2266424 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.0978. Min Act: -0.1700
Data Index: 4912756 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.0353. Min Act: -0.1700
Data Index: 8829963 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.0353. Min Act: -0.1700
Data Index: 359859 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.0040. Min Act: -0.1700
Data Index: 927430 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4728. Min Range: -8.4728
Max Act: 7.0040. Min Act: -0.1700
Data Index: 2457526 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4728. Min Range: -8.4728
Max Act: 6.9415. Min Act: -0.1700
Data Index: 2579679 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4728. Min Range: -8.4728
Max Act: 6.9415. Min Act: -0.1700
Data Index: 4912754 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19