Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.9650. Min Act: -0.1700
Data Index: 4263768 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.8400. Min Act: -0.1700
Data Index: 7677438 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.8400. Min Act: -0.1700
Data Index: 6003577 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.8088. Min Act: -0.1700
Data Index: 624539 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.7775. Min Act: -0.1700
Data Index: 4813525 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.7463. Min Act: -0.1700
Data Index: 8054918 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6838. Min Act: -0.1700
Data Index: 8781062 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.7150. Min Act: -0.1700
Data Index: 9943 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6525. Min Act: -0.1700
Data Index: 4463550 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6213. Min Act: -0.1700
Data Index: 5340414 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.5900. Min Act: -0.1700
Data Index: 4669631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.5588. Min Act: -0.1700
Data Index: 446836 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.5588. Min Act: -0.1700
Data Index: 3177246 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.5275. Min Act: -0.1700
Data Index: 2066736 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.5275. Min Act: -0.1700
Data Index: 2118973 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 357764 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4963. Min Act: -0.1700
Data Index: 5946775 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4338. Min Act: -0.1700
Data Index: 6913040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 6062218 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4963. Min Act: -0.1700
Data Index: 691638 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19