Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.6400. Min Act: -0.1700
Data Index: 1070040 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.5463. Min Act: -0.1700
Data Index: 6087885 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.5463. Min Act: -0.1700
Data Index: 7028708 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.4525. Min Act: -0.1700
Data Index: 8140127 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.4525. Min Act: -0.1700
Data Index: 3367735 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.4213. Min Act: -0.1700
Data Index: 63598 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.4213. Min Act: -0.1700
Data Index: 2595033 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.3900. Min Act: -0.1700
Data Index: 8375100 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.3588. Min Act: -0.1700
Data Index: 2489517 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.3588. Min Act: -0.1700
Data Index: 2035911 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.3275. Min Act: -0.1700
Data Index: 7389102 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2963. Min Act: -0.1700
Data Index: 1420524 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2963. Min Act: -0.1700
Data Index: 6988528 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.3275. Min Act: -0.1700
Data Index: 2274389 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.3275. Min Act: -0.1700
Data Index: 6095076 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2650. Min Act: -0.1700
Data Index: 6368911 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2963. Min Act: -0.1700
Data Index: 1407969 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2607729 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2650. Min Act: -0.1700
Data Index: 6736906 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6400. Min Range: -4.6400
Max Act: 4.2650. Min Act: -0.1700
Data Index: 7848343 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19