Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.5185. Min Act: -0.1700
Data Index: 8363023 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.5185. Min Act: -0.1700
Data Index: 3909839 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.5185. Min Act: -0.1700
Data Index: 2017086 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.4872. Min Act: -0.1700
Data Index: 8266331 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.3935. Min Act: -0.1700
Data Index: 6552803 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.3310. Min Act: -0.1700
Data Index: 3241132 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.2997. Min Act: -0.1700
Data Index: 221764 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.2372. Min Act: -0.1700
Data Index: 8563384 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.2372. Min Act: -0.1700
Data Index: 2999125 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.2060. Min Act: -0.1700
Data Index: 6652188 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1435. Min Act: -0.1700
Data Index: 5687944 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1435. Min Act: -0.1700
Data Index: 5019347 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1122. Min Act: -0.1700
Data Index: 1445301 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.0810. Min Act: -0.1700
Data Index: 1554066 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1435. Min Act: -0.1700
Data Index: 1564160 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1122. Min Act: -0.1700
Data Index: 6014947 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1122. Min Act: -0.1700
Data Index: 3626647 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1122. Min Act: -0.1700
Data Index: 2848041 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.1122. Min Act: -0.1700
Data Index: 188435 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5185. Min Range: -5.5185
Max Act: 5.0810. Min Act: -0.1700
Data Index: 5372277 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19