Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5156 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.6396. Min Act: -0.1700
Data Index: 1904183 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.5771. Min Act: -0.1700
Data Index: 7934465 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.5458. Min Act: -0.1700
Data Index: 5994267 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.5146. Min Act: -0.1700
Data Index: 1128543 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4833. Min Act: -0.1700
Data Index: 4754147 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.5146. Min Act: -0.1700
Data Index: 6911934 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4833. Min Act: -0.1700
Data Index: 5738136 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.5146. Min Act: -0.1700
Data Index: 3531427 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.5146. Min Act: -0.1700
Data Index: 1484579 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4833. Min Act: -0.1700
Data Index: 6067281 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 937941 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 5219625 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 244093 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4208. Min Act: -0.1700
Data Index: 8091819 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 993360 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 4981835 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 4226543 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4521. Min Act: -0.1700
Data Index: 1094123 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4208. Min Act: -0.1700
Data Index: 6381847 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6396. Min Range: -5.6396
Max Act: 5.4208. Min Act: -0.1700
Data Index: 4581507 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19