Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4238 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0360. Min Range: -11.0360
Max Act: 11.0360. Min Act: -0.1700
Data Index: 34573 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.5360. Min Act: -0.1700
Data Index: 6143592 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.2235. Min Act: -0.1700
Data Index: 1242562 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.3485. Min Act: -0.1700
Data Index: 5230842 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.1610. Min Act: -0.1700
Data Index: 6649880 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.1610. Min Act: -0.1700
Data Index: 161905 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.0985. Min Act: -0.1700
Data Index: 1595251 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.0360. Min Act: -0.1700
Data Index: 377408 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.0360. Min Act: -0.1700
Data Index: 758945 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.0360. Min Act: -0.1700
Data Index: 4052350 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.0360. Min Act: -0.1700
Data Index: 1826211 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0360. Min Range: -11.0360
Max Act: 10.0360. Min Act: -0.1700
Data Index: 7802205 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.9110. Min Act: -0.1700
Data Index: 3121128 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.9110. Min Act: -0.1700
Data Index: 3112909 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.7860. Min Act: -0.1700
Data Index: 722662 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.8485. Min Act: -0.1700
Data Index: 4270927 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.8485. Min Act: -0.1700
Data Index: 4793710 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.8485. Min Act: -0.1700
Data Index: 3339915 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.8485. Min Act: -0.1700
Data Index: 6169232 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0360. Min Range: -11.0360
Max Act: 9.8485. Min Act: -0.1700
Data Index: 5620468 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19