Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1157 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.6058. Min Act: -0.1700
Data Index: 3701954 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.4808. Min Act: -0.1700
Data Index: 138245 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.4808. Min Act: -0.1700
Data Index: 4210619 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.4496. Min Act: -0.1700
Data Index: 6486154 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3871. Min Act: -0.1700
Data Index: 1169315 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3871. Min Act: -0.1700
Data Index: 1298834 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3871. Min Act: -0.1700
Data Index: 1624063 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3871. Min Act: -0.1700
Data Index: 2061390 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3558. Min Act: -0.1700
Data Index: 1109774 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3558. Min Act: -0.1700
Data Index: 2805811 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3246. Min Act: -0.1700
Data Index: 1109779 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3558. Min Act: -0.1700
Data Index: 869554 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3558. Min Act: -0.1700
Data Index: 2091341 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.3246. Min Act: -0.1700
Data Index: 644702 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.2933. Min Act: -0.1700
Data Index: 1566565 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.2933. Min Act: -0.1700
Data Index: 5644094 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.2933. Min Act: -0.1700
Data Index: 1914969 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.2620. Min Act: -0.1700
Data Index: 1353259 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.2933. Min Act: -0.1700
Data Index: 1189572 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6058. Min Range: -4.6058
Max Act: 4.2620. Min Act: -0.1700
Data Index: 4119155 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19