Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4980 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1244. Min Range: -5.1244
Max Act: 5.1244. Min Act: -0.1700
Data Index: 2311731 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1244. Min Range: -5.1244
Max Act: 5.0932. Min Act: -0.1700
Data Index: 4125666 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1244. Min Range: -5.1244
Max Act: 5.0307. Min Act: -0.1700
Data Index: 279777 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.9369. Min Act: -0.1700
Data Index: 7256577 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.9057. Min Act: -0.1700
Data Index: 123979 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.8744. Min Act: -0.1700
Data Index: 4495515 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.8744. Min Act: -0.1700
Data Index: 2150692 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.8744. Min Act: -0.1700
Data Index: 242051 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.8432. Min Act: -0.1700
Data Index: 6250371 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.8432. Min Act: -0.1700
Data Index: 2324466 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7807. Min Act: -0.1700
Data Index: 2939142 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7807. Min Act: -0.1700
Data Index: 3489173 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7807. Min Act: -0.1700
Data Index: 7378425 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7807. Min Act: -0.1700
Data Index: 4315793 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7494. Min Act: -0.1700
Data Index: 6994581 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7494. Min Act: -0.1700
Data Index: 8084048 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7494. Min Act: -0.1700
Data Index: 6220091 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7494. Min Act: -0.1700
Data Index: 7025281 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.7182. Min Act: -0.1700
Data Index: 7391249 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1244. Min Range: -5.1244
Max Act: 4.6869. Min Act: -0.1700
Data Index: 242053 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19