Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.6135. Min Act: -0.1700
Data Index: 2555541 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.3635. Min Act: -0.1700
Data Index: 392115 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.3322. Min Act: -0.1700
Data Index: 6540133 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.2697. Min Act: -0.1700
Data Index: 3562115 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.2072. Min Act: -0.1700
Data Index: 7896597 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.2072. Min Act: -0.1700
Data Index: 8647144 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.1135. Min Act: -0.1700
Data Index: 5945311 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.0822. Min Act: -0.1700
Data Index: 2974982 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.0822. Min Act: -0.1700
Data Index: 1354751 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.0510. Min Act: -0.1700
Data Index: 2106290 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6135. Min Range: -7.6135
Max Act: 7.0510. Min Act: -0.1700
Data Index: 2535676 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9885. Min Act: -0.1700
Data Index: 8680449 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9885. Min Act: -0.1700
Data Index: 4707814 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9885. Min Act: -0.1700
Data Index: 7738946 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9572. Min Act: -0.1700
Data Index: 8343342 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9572. Min Act: -0.1700
Data Index: 3147340 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9572. Min Act: -0.1700
Data Index: 4799733 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9260. Min Act: -0.1700
Data Index: 1352755 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.8947. Min Act: -0.1700
Data Index: 1869773 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6135. Min Range: -7.6135
Max Act: 6.9260. Min Act: -0.1700
Data Index: 418232 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19