Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2145. Min Range: -7.2145
Max Act: 7.2145. Min Act: -0.1700
Data Index: 860212 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.9958. Min Act: -0.1700
Data Index: 3172132 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.9333. Min Act: -0.1700
Data Index: 548408 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.9645. Min Act: -0.1700
Data Index: 3573660 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.8708. Min Act: -0.1700
Data Index: 5317650 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.7458. Min Act: -0.1700
Data Index: 5664633 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.7458. Min Act: -0.1700
Data Index: 3001351 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.7458. Min Act: -0.1700
Data Index: 8377622 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6833. Min Act: -0.1700
Data Index: 4509169 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6833. Min Act: -0.1700
Data Index: 7953286 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6520. Min Act: -0.1700
Data Index: 7168981 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6833. Min Act: -0.1700
Data Index: 2535004 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6833. Min Act: -0.1700
Data Index: 2422303 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6833. Min Act: -0.1700
Data Index: 7949051 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6208. Min Act: -0.1700
Data Index: 8148388 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6520. Min Act: -0.1700
Data Index: 8722032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6520. Min Act: -0.1700
Data Index: 2574792 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6208. Min Act: -0.1700
Data Index: 6719751 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.6208. Min Act: -0.1700
Data Index: 4971121 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2145. Min Range: -7.2145
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5159180 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19