Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.8214. Min Act: -0.1700
Data Index: 3848476 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.8214. Min Act: -0.1700
Data Index: 2907955 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.3839. Min Act: -0.1700
Data Index: 8592028 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.2589. Min Act: -0.1700
Data Index: 8476114 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.2589. Min Act: -0.1700
Data Index: 2204001 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4504392 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.1651. Min Act: -0.1700
Data Index: 7994841 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.1339. Min Act: -0.1700
Data Index: 4881756 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.1026. Min Act: -0.1700
Data Index: 4837334 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.1026. Min Act: -0.1700
Data Index: 2965797 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0713. Min Act: -0.1700
Data Index: 5385004 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.1026. Min Act: -0.1700
Data Index: 4903037 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0713. Min Act: -0.1700
Data Index: 3112056 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0713. Min Act: -0.1700
Data Index: 830540 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0713. Min Act: -0.1700
Data Index: 3112064 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0401. Min Act: -0.1700
Data Index: 3648426 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0401. Min Act: -0.1700
Data Index: 3709253 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0401. Min Act: -0.1700
Data Index: 8318058 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8214. Min Range: -4.8214
Max Act: 4.0088. Min Act: -0.1700
Data Index: 113283 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8214. Min Range: -4.8214
Max Act: 3.9776. Min Act: -0.1700
Data Index: 6645724 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19