Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.7296. Min Act: -0.1700
Data Index: 5374325 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.4483. Min Act: -0.1700
Data Index: 6219463 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.4483. Min Act: -0.1700
Data Index: 4556246 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.4170. Min Act: -0.1700
Data Index: 776486 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.4483. Min Act: -0.1700
Data Index: 3748062 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3858. Min Act: -0.1700
Data Index: 4432752 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3545. Min Act: -0.1700
Data Index: 1171 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3545. Min Act: -0.1700
Data Index: 5392878 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3858. Min Act: -0.1700
Data Index: 3922104 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3545. Min Act: -0.1700
Data Index: 4432761 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3858. Min Act: -0.1700
Data Index: 2430234 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3545. Min Act: -0.1700
Data Index: 5020824 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3233. Min Act: -0.1700
Data Index: 90309 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8060961 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.2920. Min Act: -0.1700
Data Index: 2088815 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8060965 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8060957 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8060959 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3545. Min Act: -0.1700
Data Index: 8371537 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7296. Min Range: -4.7296
Max Act: 4.3233. Min Act: -0.1700
Data Index: 6127550 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19