Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.4680. Min Act: -0.1700
Data Index: 5896691 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.4055. Min Act: -0.1700
Data Index: 254372 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.3430. Min Act: -0.1700
Data Index: 264158 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.4055. Min Act: -0.1700
Data Index: 7221827 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.2805. Min Act: -0.1700
Data Index: 1845417 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.2180. Min Act: -0.1700
Data Index: 750373 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0617. Min Act: -0.1700
Data Index: 6709409 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0929. Min Act: -0.1700
Data Index: 2165019 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0617. Min Act: -0.1700
Data Index: 8331971 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.1242. Min Act: -0.1700
Data Index: 6451594 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0617. Min Act: -0.1700
Data Index: 3931803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0929. Min Act: -0.1700
Data Index: 4065564 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0617. Min Act: -0.1700
Data Index: 5059270 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1315745 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1416348 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1905354 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4680. Min Range: -4.4680
Max Act: 4.0304. Min Act: -0.1700
Data Index: 3795157 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4680. Min Range: -4.4680
Max Act: 3.9992. Min Act: -0.1700
Data Index: 1704 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4680. Min Range: -4.4680
Max Act: 3.9992. Min Act: -0.1700
Data Index: 3967129 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4680. Min Range: -4.4680
Max Act: 3.9992. Min Act: -0.1700
Data Index: 5569012 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19