Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.5672. Min Act: -0.1700
Data Index: 2653289 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.5047. Min Act: -0.1700
Data Index: 2994556 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.4422. Min Act: -0.1700
Data Index: 6234217 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.3797. Min Act: -0.1700
Data Index: 1087804 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.3485. Min Act: -0.1700
Data Index: 2410122 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.3797. Min Act: -0.1700
Data Index: 5822087 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.3172. Min Act: -0.1700
Data Index: 1490219 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.2547. Min Act: -0.1700
Data Index: 4739314 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.2235. Min Act: -0.1700
Data Index: 4309301 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1922. Min Act: -0.1700
Data Index: 8737879 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1922. Min Act: -0.1700
Data Index: 7526728 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1922. Min Act: -0.1700
Data Index: 3022645 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1297. Min Act: -0.1700
Data Index: 3493206 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1297. Min Act: -0.1700
Data Index: 5790244 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1297. Min Act: -0.1700
Data Index: 5679522 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1297. Min Act: -0.1700
Data Index: 5955193 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.1297. Min Act: -0.1700
Data Index: 2953290 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.0985. Min Act: -0.1700
Data Index: 2800344 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.0672. Min Act: -0.1700
Data Index: 6541554 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5672. Min Range: -7.5672
Max Act: 7.0985. Min Act: -0.1700
Data Index: 7875858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19