Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.7199. Min Act: -0.1700
Data Index: 5868738 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.4851. Min Act: -0.1700
Data Index: 6989982 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.4694. Min Act: -0.1700
Data Index: 148932 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.4381. Min Act: -0.1700
Data Index: 5278056 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3754. Min Act: -0.1700
Data Index: 218921 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3597. Min Act: -0.1700
Data Index: 1128847 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3597. Min Act: -0.1700
Data Index: 8725139 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3754. Min Act: -0.1700
Data Index: 2902121 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3283. Min Act: -0.1700
Data Index: 873908 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3283. Min Act: -0.1700
Data Index: 5016666 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3126. Min Act: -0.1700
Data Index: 1696088 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.3440. Min Act: -0.1700
Data Index: 6953567 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2969. Min Act: -0.1700
Data Index: 4382665 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2969. Min Act: -0.1700
Data Index: 1422720 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2969. Min Act: -0.1700
Data Index: 602627 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2812. Min Act: -0.1700
Data Index: 1377243 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2812. Min Act: -0.1700
Data Index: 4376242 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2812. Min Act: -0.1700
Data Index: 3704144 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2655. Min Act: -0.1700
Data Index: 4387768 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7199. Min Range: -3.7199
Max Act: 3.2655. Min Act: -0.1700
Data Index: 5691684 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19