Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1539 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.6794. Min Act: -0.1700
Data Index: 3579106 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.4919. Min Act: -0.1700
Data Index: 398461 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.3669. Min Act: -0.1700
Data Index: 3239583 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.2419. Min Act: -0.1700
Data Index: 4719164 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.2419. Min Act: -0.1700
Data Index: 1133596 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.2419. Min Act: -0.1700
Data Index: 4781144 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.2419. Min Act: -0.1700
Data Index: 7954156 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.0856. Min Act: -0.1700
Data Index: 1135069 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.0856. Min Act: -0.1700
Data Index: 3254986 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6794. Min Range: -8.6794
Max Act: 8.0231. Min Act: -0.1700
Data Index: 3532683 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9919. Min Act: -0.1700
Data Index: 4274325 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9919. Min Act: -0.1700
Data Index: 2782894 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9606. Min Act: -0.1700
Data Index: 7196734 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 4165667 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 2116124 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 1216022 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.8981. Min Act: -0.1700
Data Index: 2510347 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.8981. Min Act: -0.1700
Data Index: 3704052 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.8669. Min Act: -0.1700
Data Index: 6852483 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6794. Min Range: -8.6794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 1830490 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19