Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2262. Min Range: -7.2262
Max Act: 7.2262. Min Act: -0.1700
Data Index: 5261886 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2262. Min Range: -7.2262
Max Act: 7.0700. Min Act: -0.1700
Data Index: 1068702 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2262. Min Range: -7.2262
Max Act: 7.0387. Min Act: -0.1700
Data Index: 5162206 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2262. Min Range: -7.2262
Max Act: 7.0075. Min Act: -0.1700
Data Index: 8275554 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.9450. Min Act: -0.1700
Data Index: 6468990 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.9450. Min Act: -0.1700
Data Index: 889408 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.9450. Min Act: -0.1700
Data Index: 6236935 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.9137. Min Act: -0.1700
Data Index: 2945802 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.9137. Min Act: -0.1700
Data Index: 5683210 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.8825. Min Act: -0.1700
Data Index: 590074 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.8825. Min Act: -0.1700
Data Index: 5231268 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.8512. Min Act: -0.1700
Data Index: 3407210 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.8200. Min Act: -0.1700
Data Index: 1141633 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.8200. Min Act: -0.1700
Data Index: 5252548 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.7887. Min Act: -0.1700
Data Index: 2118981 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.7887. Min Act: -0.1700
Data Index: 2578162 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.7575. Min Act: -0.1700
Data Index: 5883322 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.7575. Min Act: -0.1700
Data Index: 890076 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.7575. Min Act: -0.1700
Data Index: 2963423 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2262. Min Range: -7.2262
Max Act: 6.7262. Min Act: -0.1700
Data Index: 5759060 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19