Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.5574. Min Act: -0.1700
Data Index: 3145408 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.5261. Min Act: -0.1700
Data Index: 6371763 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.5261. Min Act: -0.1700
Data Index: 4745156 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.4949. Min Act: -0.1700
Data Index: 6628680 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.4949. Min Act: -0.1700
Data Index: 123086 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.4949. Min Act: -0.1700
Data Index: 7024302 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.4011. Min Act: -0.1700
Data Index: 8189722 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3386. Min Act: -0.1700
Data Index: 8286618 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3386. Min Act: -0.1700
Data Index: 7090848 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3386. Min Act: -0.1700
Data Index: 8611312 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3386. Min Act: -0.1700
Data Index: 4775047 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3074. Min Act: -0.1700
Data Index: 5786929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3074. Min Act: -0.1700
Data Index: 2664954 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3074. Min Act: -0.1700
Data Index: 11890 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3074. Min Act: -0.1700
Data Index: 7014809 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.3386. Min Act: -0.1700
Data Index: 2413715 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.2761. Min Act: -0.1700
Data Index: 5483105 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.2449. Min Act: -0.1700
Data Index: 3002765 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.2449. Min Act: -0.1700
Data Index: 2784739 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5574. Min Range: -5.5574
Max Act: 5.2449. Min Act: -0.1700
Data Index: 7960336 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19