Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.5059. Min Act: -0.1700
Data Index: 2968160 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.4121. Min Act: -0.1700
Data Index: 2758497 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.4121. Min Act: -0.1700
Data Index: 4941460 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.3809. Min Act: -0.1700
Data Index: 4253824 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1962722 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.2559. Min Act: -0.1700
Data Index: 19111 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.2246. Min Act: -0.1700
Data Index: 1298863 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.2246. Min Act: -0.1700
Data Index: 3876382 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.2246. Min Act: -0.1700
Data Index: 657201 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1934. Min Act: -0.1700
Data Index: 8797398 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 27976 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1934. Min Act: -0.1700
Data Index: 8812795 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1309. Min Act: -0.1700
Data Index: 2717618 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 2468580 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 7070598 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 3350895 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 1701023 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 5215041 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1621. Min Act: -0.1700
Data Index: 4562097 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5059. Min Range: -7.5059
Max Act: 7.1309. Min Act: -0.1700
Data Index: 4886618 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19