Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9834. Min Act: -0.1700
Data Index: 1356631 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9580. Min Act: -0.1700
Data Index: 5230054 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9580. Min Act: -0.1700
Data Index: 5930319 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9580. Min Act: -0.1700
Data Index: 4101513 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9410. Min Act: -0.1700
Data Index: 3201381 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9325. Min Act: -0.1700
Data Index: 4407225 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9240. Min Act: -0.1700
Data Index: 2197411 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9155. Min Act: -0.1700
Data Index: 1607150 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9240. Min Act: -0.1695
Data Index: 3380391 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9155. Min Act: -0.1700
Data Index: 7064183 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9240. Min Act: -0.1700
Data Index: 8688283 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9070. Min Act: -0.1700
Data Index: 7229438 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.9070. Min Act: -0.1700
Data Index: 7444828 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8985. Min Act: -0.1700
Data Index: 4635477 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8985. Min Act: -0.1700
Data Index: 6879066 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8985. Min Act: -0.1700
Data Index: 3674052 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8900. Min Act: -0.1700
Data Index: 8384237 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8814. Min Act: -0.1700
Data Index: 8208739 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8900. Min Act: -0.1700
Data Index: 364396 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9834. Min Range: -1.9834
Max Act: 1.8985. Min Act: -0.1698
Data Index: 5409491 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19