Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5754 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.7071. Min Act: -0.1700
Data Index: 426128 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.5509. Min Act: -0.1700
Data Index: 7776367 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4259. Min Act: -0.1700
Data Index: 7462680 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1554297 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4571. Min Act: -0.1700
Data Index: 6672375 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3946. Min Act: -0.1700
Data Index: 5955556 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3321. Min Act: -0.1700
Data Index: 1169905 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3634. Min Act: -0.1700
Data Index: 1378254 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3634. Min Act: -0.1700
Data Index: 6257211 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3321. Min Act: -0.1700
Data Index: 2835179 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3009. Min Act: -0.1700
Data Index: 2246871 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3321. Min Act: -0.1700
Data Index: 6713402 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3321. Min Act: -0.1700
Data Index: 2246874 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.2696. Min Act: -0.1700
Data Index: 6504954 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3009. Min Act: -0.1700
Data Index: 2427989 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3009. Min Act: -0.1700
Data Index: 4276579 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.2384. Min Act: -0.1700
Data Index: 134734 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.2696. Min Act: -0.1700
Data Index: 2402480 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.2696. Min Act: -0.1700
Data Index: 7489276 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.2384. Min Act: -0.1700
Data Index: 3841532 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19