Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2549. Min Range: -5.2549
Max Act: 5.2549. Min Act: -0.1700
Data Index: 1375172 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.9424. Min Act: -0.1700
Data Index: 3843589 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.9112. Min Act: -0.1700
Data Index: 7133662 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.9112. Min Act: -0.1700
Data Index: 7426824 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.8799. Min Act: -0.1700
Data Index: 5122790 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.8487. Min Act: -0.1700
Data Index: 3553257 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.8487. Min Act: -0.1700
Data Index: 7090713 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.8174. Min Act: -0.1700
Data Index: 2113281 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.8174. Min Act: -0.1700
Data Index: 4743361 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.7862. Min Act: -0.1700
Data Index: 2129783 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.7549. Min Act: -0.1700
Data Index: 3500294 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6924. Min Act: -0.1700
Data Index: 2451070 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5998849 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6612. Min Act: -0.1700
Data Index: 6224167 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6612. Min Act: -0.1700
Data Index: 1841189 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6612. Min Act: -0.1700
Data Index: 2899437 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6612. Min Act: -0.1700
Data Index: 3027214 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6924. Min Act: -0.1700
Data Index: 8515126 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6612. Min Act: -0.1700
Data Index: 2034966 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2549. Min Range: -5.2549
Max Act: 4.6299. Min Act: -0.1700
Data Index: 409977 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19