Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.5847. Min Act: -0.1700
Data Index: 671253 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.5535. Min Act: -0.1700
Data Index: 7934834 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.5222. Min Act: -0.1700
Data Index: 1439930 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.4910. Min Act: -0.1700
Data Index: 707772 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.4597. Min Act: -0.1700
Data Index: 8511224 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.4285. Min Act: -0.1700
Data Index: 7695952 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3972. Min Act: -0.1700
Data Index: 4713649 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.4285. Min Act: -0.1700
Data Index: 7817432 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3972. Min Act: -0.1700
Data Index: 2242142 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3660. Min Act: -0.1700
Data Index: 6141524 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3972. Min Act: -0.1700
Data Index: 1419738 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3972. Min Act: -0.1700
Data Index: 3980419 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3347. Min Act: -0.1700
Data Index: 8218030 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3660. Min Act: -0.1700
Data Index: 4513265 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3035. Min Act: -0.1700
Data Index: 1740450 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3347. Min Act: -0.1700
Data Index: 5431668 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3347. Min Act: -0.1700
Data Index: 3246919 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3035. Min Act: -0.1700
Data Index: 3819818 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3035. Min Act: -0.1700
Data Index: 2790254 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5847. Min Range: -5.5847
Max Act: 5.3035. Min Act: -0.1700
Data Index: 1749575 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19