Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3750 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.4195. Min Act: -0.1700
Data Index: 5064834 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.3570. Min Act: -0.1700
Data Index: 4067186 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.3570. Min Act: -0.1700
Data Index: 4148658 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.3257. Min Act: -0.1700
Data Index: 3598877 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.2007. Min Act: -0.1700
Data Index: 2369456 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.1695. Min Act: -0.1700
Data Index: 1547066 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.1695. Min Act: -0.1700
Data Index: 3033297 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.1695. Min Act: -0.1700
Data Index: 2908940 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.0757. Min Act: -0.1700
Data Index: 1368953 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.0757. Min Act: -0.1700
Data Index: 4017310 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.0445. Min Act: -0.1700
Data Index: 2411442 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.0757. Min Act: -0.1700
Data Index: 1543083 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.0132. Min Act: -0.1700
Data Index: 7869451 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4195. Min Range: -7.4195
Max Act: 7.0445. Min Act: -0.1700
Data Index: 5599790 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4195. Min Range: -7.4195
Max Act: 6.9820. Min Act: -0.1700
Data Index: 1266807 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4195. Min Range: -7.4195
Max Act: 6.9507. Min Act: -0.1700
Data Index: 8198890 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4195. Min Range: -7.4195
Max Act: 6.9195. Min Act: -0.1700
Data Index: 4852504 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4195. Min Range: -7.4195
Max Act: 6.9507. Min Act: -0.1700
Data Index: 3876738 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4195. Min Range: -7.4195
Max Act: 6.9507. Min Act: -0.1700
Data Index: 5732999 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4195. Min Range: -7.4195
Max Act: 6.9195. Min Act: -0.1700
Data Index: 5488408 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19