Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4752 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.4170. Min Act: -0.1700
Data Index: 7776053 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.3543. Min Act: -0.1700
Data Index: 2689497 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.3543. Min Act: -0.1700
Data Index: 3638477 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.3229. Min Act: -0.1700
Data Index: 6663651 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.3229. Min Act: -0.1700
Data Index: 6560766 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2915. Min Act: -0.1700
Data Index: 1183323 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2758. Min Act: -0.1700
Data Index: 8634256 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2915. Min Act: -0.1700
Data Index: 2750969 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2601. Min Act: -0.1700
Data Index: 7731460 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2601. Min Act: -0.1700
Data Index: 3762827 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2444. Min Act: -0.1700
Data Index: 1290992 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.2287. Min Act: -0.1700
Data Index: 1980607 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1815. Min Act: -0.1700
Data Index: 8428945 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1972. Min Act: -0.1700
Data Index: 896359 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1972. Min Act: -0.1700
Data Index: 5108801 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1972. Min Act: -0.1700
Data Index: 3337035 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1815. Min Act: -0.1700
Data Index: 4017407 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1658. Min Act: -0.1700
Data Index: 7520782 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1658. Min Act: -0.1700
Data Index: 1254980 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4170. Min Range: -3.4170
Max Act: 3.1500. Min Act: -0.1700
Data Index: 1947658 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19