Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.3289. Min Act: -0.1700
Data Index: 6512207 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.2664. Min Act: -0.1700
Data Index: 6803250 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.1414. Min Act: -0.1700
Data Index: 919645 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.1414. Min Act: -0.1700
Data Index: 1853814 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.1102. Min Act: -0.1700
Data Index: 2226042 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.1102. Min Act: -0.1700
Data Index: 45370 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0789. Min Act: -0.1700
Data Index: 7181593 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0789. Min Act: -0.1700
Data Index: 8365871 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0477. Min Act: -0.1700
Data Index: 3137350 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0477. Min Act: -0.1700
Data Index: 8816641 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0164. Min Act: -0.1700
Data Index: 2106974 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0477. Min Act: -0.1700
Data Index: 3210710 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0477. Min Act: -0.1700
Data Index: 7431213 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3289. Min Range: -5.3289
Max Act: 4.9852. Min Act: -0.1700
Data Index: 1594627 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0164. Min Act: -0.1700
Data Index: 1978049 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0164. Min Act: -0.1700
Data Index: 1029030 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0164. Min Act: -0.1700
Data Index: 7083066 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3289. Min Range: -5.3289
Max Act: 5.0164. Min Act: -0.1700
Data Index: 3395602 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3289. Min Range: -5.3289
Max Act: 4.9539. Min Act: -0.1700
Data Index: 1501005 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3289. Min Range: -5.3289
Max Act: 4.9852. Min Act: -0.1700
Data Index: 2765173 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19