Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.5073. Min Act: -0.1700
Data Index: 8650307 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.4289. Min Act: -0.1700
Data Index: 8750935 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.3348. Min Act: -0.1700
Data Index: 6911249 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2878. Min Act: -0.1700
Data Index: 301160 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2878. Min Act: -0.1700
Data Index: 252107 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2563. Min Act: -0.1700
Data Index: 6612186 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2406. Min Act: -0.1700
Data Index: 5529811 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2406. Min Act: -0.1700
Data Index: 359505 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2249. Min Act: -0.1700
Data Index: 1306657 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.1935. Min Act: -0.1700
Data Index: 5497124 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2249. Min Act: -0.1700
Data Index: 7722489 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2092. Min Act: -0.1700
Data Index: 8708674 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2092. Min Act: -0.1700
Data Index: 8664685 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2249. Min Act: -0.1700
Data Index: 2666207 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.2092. Min Act: -0.1700
Data Index: 5009172 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.1935. Min Act: -0.1700
Data Index: 1112056 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.1935. Min Act: -0.1700
Data Index: 3852481 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.1935. Min Act: -0.1700
Data Index: 1544527 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.1935. Min Act: -0.1700
Data Index: 133397 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5073. Min Range: -3.5073
Max Act: 3.1935. Min Act: -0.1700
Data Index: 7840908 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19