Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2119 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.7493. Min Act: -0.1700
Data Index: 3021226 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.6556. Min Act: -0.1700
Data Index: 1620866 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.5306. Min Act: -0.1700
Data Index: 6100739 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.4368. Min Act: -0.1700
Data Index: 3361169 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.4681. Min Act: -0.1700
Data Index: 5654052 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.4056. Min Act: -0.1700
Data Index: 6095131 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.4056. Min Act: -0.1700
Data Index: 3063138 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.4056. Min Act: -0.1700
Data Index: 5365718 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.3431. Min Act: -0.1700
Data Index: 4716261 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.3431. Min Act: -0.1700
Data Index: 2273227 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.3431. Min Act: -0.1700
Data Index: 3697774 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.3118. Min Act: -0.1700
Data Index: 3370810 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.3118. Min Act: -0.1700
Data Index: 1085318 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2806. Min Act: -0.1700
Data Index: 6441791 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2493. Min Act: -0.1700
Data Index: 3157292 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2493. Min Act: -0.1700
Data Index: 5300796 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2493. Min Act: -0.1700
Data Index: 2211944 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2806. Min Act: -0.1700
Data Index: 7744542 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2493. Min Act: -0.1700
Data Index: 7603626 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7493. Min Range: -7.7493
Max Act: 7.2806. Min Act: -0.1700
Data Index: 8614304 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19