Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4840 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 2873382 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1882. Min Act: -0.1700
Data Index: 8280604 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1882. Min Act: -0.1700
Data Index: 3747522 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1882. Min Act: -0.1700
Data Index: 8715707 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1569. Min Act: -0.1700
Data Index: 6736504 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1882. Min Act: -0.1700
Data Index: 8422323 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1257. Min Act: -0.1700
Data Index: 5682392 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1257. Min Act: -0.1700
Data Index: 1571012 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1569. Min Act: -0.1700
Data Index: 7314911 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0944. Min Act: -0.1700
Data Index: 7019216 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.1257. Min Act: -0.1700
Data Index: 4551471 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0944. Min Act: -0.1700
Data Index: 8828331 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0944. Min Act: -0.1700
Data Index: 3482088 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0944. Min Act: -0.1700
Data Index: 7853092 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0631. Min Act: -0.1700
Data Index: 4996847 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0631. Min Act: -0.1700
Data Index: 3573797 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0319. Min Act: -0.1700
Data Index: 6220831 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0631. Min Act: -0.1700
Data Index: 29989 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0319. Min Act: -0.1700
Data Index: 7489971 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2507. Min Range: -4.2507
Max Act: 4.0319. Min Act: -0.1700
Data Index: 704210 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19