Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.3945. Min Act: -0.1700
Data Index: 2983546 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.3632. Min Act: -0.1700
Data Index: 3566344 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.1445. Min Act: -0.1700
Data Index: 5164402 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.0820. Min Act: -0.1700
Data Index: 8226149 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.0820. Min Act: -0.1700
Data Index: 6103315 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.0507. Min Act: -0.1700
Data Index: 533541 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.0507. Min Act: -0.1700
Data Index: 8372072 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.0507. Min Act: -0.1700
Data Index: 8037871 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3945. Min Range: -6.3945
Max Act: 6.0195. Min Act: -0.1700
Data Index: 1240576 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.9570. Min Act: -0.1700
Data Index: 7498670 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.9882. Min Act: -0.1700
Data Index: 5900990 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.9882. Min Act: -0.1700
Data Index: 1023448 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.9882. Min Act: -0.1700
Data Index: 7020797 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.9570. Min Act: -0.1700
Data Index: 485719 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.9257. Min Act: -0.1700
Data Index: 3525994 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.8945. Min Act: -0.1700
Data Index: 4688656 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.8632. Min Act: -0.1700
Data Index: 4261015 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.8320. Min Act: -0.1700
Data Index: 5530227 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.8632. Min Act: -0.1700
Data Index: 1360389 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3945. Min Range: -6.3945
Max Act: 5.8632. Min Act: -0.1700
Data Index: 8694052 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19