Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2145. Min Range: -6.2145
Max Act: 6.2145. Min Act: -0.1700
Data Index: 1334031 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2145. Min Range: -6.2145
Max Act: 6.1208. Min Act: -0.1700
Data Index: 4766772 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2145. Min Range: -6.2145
Max Act: 6.0270. Min Act: -0.1700
Data Index: 4215256 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2145. Min Range: -6.2145
Max Act: 6.0270. Min Act: -0.1700
Data Index: 6958445 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2145. Min Range: -6.2145
Max Act: 6.0270. Min Act: -0.1700
Data Index: 4338725 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.9645. Min Act: -0.1700
Data Index: 4237605 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.9333. Min Act: -0.1700
Data Index: 4817379 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.9333. Min Act: -0.1700
Data Index: 2949070 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.8708. Min Act: -0.1700
Data Index: 1444464 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.9020. Min Act: -0.1700
Data Index: 2721115 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.9020. Min Act: -0.1700
Data Index: 3914504 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.8708. Min Act: -0.1700
Data Index: 3361270 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.8395. Min Act: -0.1700
Data Index: 8506602 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.8395. Min Act: -0.1700
Data Index: 1044322 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.8083. Min Act: -0.1700
Data Index: 36057 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.7770. Min Act: -0.1700
Data Index: 6002671 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.7770. Min Act: -0.1700
Data Index: 1520884 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.7770. Min Act: -0.1700
Data Index: 1030106 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.7770. Min Act: -0.1700
Data Index: 2540625 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2145. Min Range: -6.2145
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5462533 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19