Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 860 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.5467. Min Act: -0.1700
Data Index: 2210035 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5023032 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.3592. Min Act: -0.1700
Data Index: 8519254 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.3279. Min Act: -0.1700
Data Index: 6215574 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.3279. Min Act: -0.1700
Data Index: 2679678 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2967. Min Act: -0.1700
Data Index: 5541832 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2967. Min Act: -0.1700
Data Index: 3231400 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2342. Min Act: -0.1700
Data Index: 1614579 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2967. Min Act: -0.1700
Data Index: 3310633 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2342. Min Act: -0.1700
Data Index: 8786937 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2029. Min Act: -0.1700
Data Index: 7098409 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.2029. Min Act: -0.1700
Data Index: 274451 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.1404. Min Act: -0.1700
Data Index: 8465715 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.1717. Min Act: -0.1700
Data Index: 4784049 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.1404. Min Act: -0.1700
Data Index: 1372124 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.1092. Min Act: -0.1700
Data Index: 8690198 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.0779. Min Act: -0.1700
Data Index: 1559822 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.1092. Min Act: -0.1700
Data Index: 3700536 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.0779. Min Act: -0.1700
Data Index: 8732154 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5467. Min Range: -6.5467
Max Act: 6.0779. Min Act: -0.1700
Data Index: 8395443 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19