Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3138. Min Range: -7.3138
Max Act: 7.3138. Min Act: -0.1700
Data Index: 24749 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3138. Min Range: -7.3138
Max Act: 7.2513. Min Act: -0.1700
Data Index: 2791224 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3138. Min Range: -7.3138
Max Act: 7.0951. Min Act: -0.1700
Data Index: 2685922 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.8763. Min Act: -0.1700
Data Index: 6249125 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.6576. Min Act: -0.1700
Data Index: 5857594 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.5013. Min Act: -0.1700
Data Index: 5298618 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.4701. Min Act: -0.1700
Data Index: 4389589 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.4076. Min Act: -0.1700
Data Index: 4892106 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.4388. Min Act: -0.1700
Data Index: 6961576 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.4076. Min Act: -0.1700
Data Index: 197928 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3763. Min Act: -0.1700
Data Index: 4257504 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3763. Min Act: -0.1700
Data Index: 6668893 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3763. Min Act: -0.1700
Data Index: 4009798 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3451. Min Act: -0.1700
Data Index: 3543588 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3451. Min Act: -0.1700
Data Index: 4885620 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3451. Min Act: -0.1700
Data Index: 8565959 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3451. Min Act: -0.1700
Data Index: 1446802 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3138. Min Act: -0.1700
Data Index: 8675147 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3138. Min Act: -0.1700
Data Index: 8744320 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3138. Min Range: -7.3138
Max Act: 6.3138. Min Act: -0.1700
Data Index: 6772769 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19