Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5714 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0136. Min Range: -7.0136
Max Act: 7.0136. Min Act: -0.1700
Data Index: 6701860 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.7948. Min Act: -0.1700
Data Index: 315368 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.6698. Min Act: -0.1700
Data Index: 5729164 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.6073. Min Act: -0.1700
Data Index: 7149852 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.4823. Min Act: -0.1700
Data Index: 2093305 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.3573. Min Act: -0.1700
Data Index: 7977828 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.3261. Min Act: -0.1700
Data Index: 1953416 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.2948. Min Act: -0.1700
Data Index: 4604136 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.2636. Min Act: -0.1700
Data Index: 7215308 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.2011. Min Act: -0.1700
Data Index: 3051398 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.2011. Min Act: -0.1700
Data Index: 6296612 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.2011. Min Act: -0.1700
Data Index: 3608475 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 2563424 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 5136663 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 2865890 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 5077582 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 2454626 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1698. Min Act: -0.1700
Data Index: 7105924 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 1349246 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0136. Min Range: -7.0136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 4975021 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19