Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4433 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.2411. Min Act: -0.1700
Data Index: 4613268 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.2411. Min Act: -0.1700
Data Index: 2456033 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.2411. Min Act: -0.1700
Data Index: 5322763 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1474. Min Act: -0.1700
Data Index: 1289266 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1474. Min Act: -0.1700
Data Index: 882131 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1474. Min Act: -0.1700
Data Index: 693927 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1474. Min Act: -0.1700
Data Index: 4390444 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1474. Min Act: -0.1700
Data Index: 6164739 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1161. Min Act: -0.1700
Data Index: 6820594 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.1161. Min Act: -0.1700
Data Index: 5493244 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0849. Min Act: -0.1700
Data Index: 2270269 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0536. Min Act: -0.1700
Data Index: 487822 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0536. Min Act: -0.1700
Data Index: 2741102 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0224. Min Act: -0.1700
Data Index: 3489553 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0536. Min Act: -0.1700
Data Index: 6124291 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0536. Min Act: -0.1700
Data Index: 2556056 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2411. Min Range: -5.2411
Max Act: 5.0224. Min Act: -0.1700
Data Index: 6371559 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2411. Min Range: -5.2411
Max Act: 4.9911. Min Act: -0.1700
Data Index: 3476641 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2411. Min Range: -5.2411
Max Act: 4.9599. Min Act: -0.1700
Data Index: 3172293 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2411. Min Range: -5.2411
Max Act: 4.9911. Min Act: -0.1700
Data Index: 1246106 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19