Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.8220. Min Act: -0.1700
Data Index: 3386190 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.6813. Min Act: -0.1700
Data Index: 643995 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.6500. Min Act: -0.1700
Data Index: 922078 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.6343. Min Act: -0.1700
Data Index: 7859522 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.6187. Min Act: -0.1700
Data Index: 6158858 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.6187. Min Act: -0.1700
Data Index: 2975757 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.5561. Min Act: -0.1700
Data Index: 5670601 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.5561. Min Act: -0.1700
Data Index: 3586165 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.5248. Min Act: -0.1700
Data Index: 6047728 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4934. Min Act: -0.1700
Data Index: 6054182 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.5091. Min Act: -0.1700
Data Index: 3799177 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.5091. Min Act: -0.1700
Data Index: 2340888 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4621. Min Act: -0.1700
Data Index: 6990145 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4778. Min Act: -0.1700
Data Index: 5469145 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4621. Min Act: -0.1700
Data Index: 2386659 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4778. Min Act: -0.1700
Data Index: 8813945 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4621. Min Act: -0.1700
Data Index: 3626406 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4464. Min Act: -0.1700
Data Index: 6133416 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4308. Min Act: -0.1700
Data Index: 985349 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8220. Min Range: -3.8220
Max Act: 3.4464. Min Act: -0.1700
Data Index: 3918228 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19