Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 310 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.2380. Min Act: -0.1700
Data Index: 2504068 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.2380. Min Act: -0.1700
Data Index: 5020503 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.1130. Min Act: -0.1700
Data Index: 8210088 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0505. Min Act: -0.1700
Data Index: 4829400 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 7458962 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 2905189 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 1154135 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 6453712 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 1153452 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 5020502 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 6071136 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 5834133 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2380. Min Range: -5.2380
Max Act: 5.0192. Min Act: -0.1700
Data Index: 5777098 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9880. Min Act: -0.1700
Data Index: 4379674 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9880. Min Act: -0.1700
Data Index: 494524 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9567. Min Act: -0.1700
Data Index: 660296 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9880. Min Act: -0.1700
Data Index: 2621462 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6318684 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9880. Min Act: -0.1700
Data Index: 1293777 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2380. Min Range: -5.2380
Max Act: 4.9880. Min Act: -0.1700
Data Index: 7206330 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19