Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.8087. Min Act: -0.1700
Data Index: 851799 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.7462. Min Act: -0.1700
Data Index: 3558432 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.6212. Min Act: -0.1700
Data Index: 7477265 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.5900. Min Act: -0.1700
Data Index: 4478783 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.5587. Min Act: -0.1700
Data Index: 4121182 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.5275. Min Act: -0.1700
Data Index: 1865213 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.5275. Min Act: -0.1700
Data Index: 7444842 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.4337. Min Act: -0.1700
Data Index: 270642 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.4337. Min Act: -0.1700
Data Index: 522308 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.4337. Min Act: -0.1700
Data Index: 5779955 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.4025. Min Act: -0.1700
Data Index: 4607932 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3712. Min Act: -0.1700
Data Index: 3825355 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3712. Min Act: -0.1700
Data Index: 5491711 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3712. Min Act: -0.1700
Data Index: 4784046 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3712. Min Act: -0.1700
Data Index: 6845694 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3712. Min Act: -0.1700
Data Index: 7728056 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3400. Min Act: -0.1700
Data Index: 2462945 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3400. Min Act: -0.1700
Data Index: 8782312 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.3087. Min Act: -0.1700
Data Index: 6540300 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8087. Min Range: -5.8087
Max Act: 5.2775. Min Act: -0.1700
Data Index: 7169543 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19