Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2554. Min Range: -7.2554
Max Act: 7.2554. Min Act: -0.1700
Data Index: 1450693 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2554. Min Range: -7.2554
Max Act: 7.1929. Min Act: -0.1700
Data Index: 1511744 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2554. Min Range: -7.2554
Max Act: 7.0679. Min Act: -0.1697
Data Index: 8150394 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2554. Min Range: -7.2554
Max Act: 7.0054. Min Act: -0.1700
Data Index: 5645005 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2554. Min Range: -7.2554
Max Act: 7.0054. Min Act: -0.1700
Data Index: 3765360 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.9116. Min Act: -0.1700
Data Index: 1879522 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.9116. Min Act: -0.1700
Data Index: 2063195 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.9116. Min Act: -0.1700
Data Index: 6192117 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.9116. Min Act: -0.1696
Data Index: 6332293 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.8491. Min Act: -0.1700
Data Index: 4525522 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.8491. Min Act: -0.1700
Data Index: 1061275 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.8491. Min Act: -0.1700
Data Index: 3937981 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.8179. Min Act: -0.1700
Data Index: 8620152 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.8179. Min Act: -0.1700
Data Index: 5982415 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.7866. Min Act: -0.1700
Data Index: 8597415 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.7554. Min Act: -0.1700
Data Index: 8691567 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.7554. Min Act: -0.1699
Data Index: 2563999 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.7866. Min Act: -0.1700
Data Index: 6389922 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.7241. Min Act: -0.1700
Data Index: 5302773 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2554. Min Range: -7.2554
Max Act: 6.7241. Min Act: -0.1700
Data Index: 4030677 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19