Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.4893. Min Act: -0.1700
Data Index: 5367968 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.4581. Min Act: -0.1700
Data Index: 5364709 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.4268. Min Act: -0.1700
Data Index: 7456327 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.3956. Min Act: -0.1700
Data Index: 2010029 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.3018. Min Act: -0.1700
Data Index: 6772175 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2706. Min Act: -0.1700
Data Index: 3745861 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2706. Min Act: -0.1700
Data Index: 7456328 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2393. Min Act: -0.1700
Data Index: 6870856 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2393. Min Act: -0.1700
Data Index: 2038424 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2081. Min Act: -0.1700
Data Index: 1349874 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2393. Min Act: -0.1700
Data Index: 6647136 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2081. Min Act: -0.1700
Data Index: 3005922 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 2983082 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1143. Min Act: -0.1700
Data Index: 3793835 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 265995 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.0831. Min Act: -0.1700
Data Index: 5387283 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1456. Min Act: -0.1700
Data Index: 4990685 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1143. Min Act: -0.1700
Data Index: 5402942 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1143. Min Act: -0.1700
Data Index: 7021722 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.0518. Min Act: -0.1700
Data Index: 7711125 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19