Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6235 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.4659. Min Act: -0.1700
Data Index: 5018272 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.3409. Min Act: -0.1700
Data Index: 8423347 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2784. Min Act: -0.1700
Data Index: 4136464 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2784. Min Act: -0.1700
Data Index: 6842476 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2471. Min Act: -0.1700
Data Index: 578417 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2159. Min Act: -0.1700
Data Index: 4598736 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2159. Min Act: -0.1700
Data Index: 4297713 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2159. Min Act: -0.1700
Data Index: 3243772 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.2159. Min Act: -0.1700
Data Index: 2420869 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1846. Min Act: -0.1700
Data Index: 6288457 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1846. Min Act: -0.1700
Data Index: 3345802 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1846. Min Act: -0.1700
Data Index: 3216361 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1846. Min Act: -0.1700
Data Index: 8416608 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1846. Min Act: -0.1700
Data Index: 490359 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1534. Min Act: -0.1700
Data Index: 4041667 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1221. Min Act: -0.1700
Data Index: 5712771 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1221. Min Act: -0.1700
Data Index: 6695544 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1534. Min Act: -0.1700
Data Index: 3348911 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1221. Min Act: -0.1700
Data Index: 239620 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4659. Min Range: -6.4659
Max Act: 6.1221. Min Act: -0.1700
Data Index: 8415653 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19