Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.3713. Min Act: -0.1700
Data Index: 5618070 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.3401. Min Act: -0.1700
Data Index: 7357262 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.3401. Min Act: -0.1700
Data Index: 3468256 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.2463. Min Act: -0.1700
Data Index: 5329200 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.2150. Min Act: -0.1700
Data Index: 8248756 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.1525. Min Act: -0.1700
Data Index: 70730 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.1213. Min Act: -0.1700
Data Index: 6926767 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.1213. Min Act: -0.1700
Data Index: 8176418 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0900. Min Act: -0.1700
Data Index: 142980 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0900. Min Act: -0.1700
Data Index: 1208933 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0900. Min Act: -0.1700
Data Index: 8250766 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0900. Min Act: -0.1700
Data Index: 5888545 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 4307846 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 3722422 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 3676274 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0275. Min Act: -0.1700
Data Index: 5190990 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 8683598 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 6596429 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 6025604 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3713. Min Range: -4.3713
Max Act: 4.0588. Min Act: -0.1700
Data Index: 5611667 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19