Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.6161. Min Act: -0.1700
Data Index: 6434133 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.4286. Min Act: -0.1700
Data Index: 4231374 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.3036. Min Act: -0.1700
Data Index: 8145209 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.1786. Min Act: -0.1700
Data Index: 8595055 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.1786. Min Act: -0.1700
Data Index: 17342 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.1473. Min Act: -0.1700
Data Index: 6666221 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.0848. Min Act: -0.1700
Data Index: 7934149 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.1161. Min Act: -0.1700
Data Index: 5325100 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.0848. Min Act: -0.1700
Data Index: 4140658 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.0848. Min Act: -0.1700
Data Index: 1794879 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6161. Min Range: -8.6161
Max Act: 8.0536. Min Act: -0.1700
Data Index: 6298395 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.9598. Min Act: -0.1700
Data Index: 6300232 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.9286. Min Act: -0.1700
Data Index: 3385768 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.8661. Min Act: -0.1700
Data Index: 7729943 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.8348. Min Act: -0.1700
Data Index: 5237489 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.8036. Min Act: -0.1700
Data Index: 2813109 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.7723. Min Act: -0.1700
Data Index: 4382097 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.7723. Min Act: -0.1700
Data Index: 8365554 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.7723. Min Act: -0.1700
Data Index: 5781178 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6161. Min Range: -8.6161
Max Act: 7.7411. Min Act: -0.1700
Data Index: 7276486 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19