Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.6335. Min Act: -0.1700
Data Index: 3065720 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.5692. Min Act: -0.1700
Data Index: 6570618 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.5530. Min Act: -0.1699
Data Index: 7255149 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.5369. Min Act: -0.1700
Data Index: 7268261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.5207. Min Act: -0.1700
Data Index: 5120414 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.5045. Min Act: -0.1700
Data Index: 618980 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.5207. Min Act: -0.1700
Data Index: 8409400 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4883. Min Act: -0.1700
Data Index: 2735300 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4883. Min Act: -0.1700
Data Index: 7255146 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4883. Min Act: -0.1700
Data Index: 8209237 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4883. Min Act: -0.1700
Data Index: 2333973 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4721. Min Act: -0.1700
Data Index: 7120051 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4721. Min Act: -0.1700
Data Index: 679425 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4721. Min Act: -0.1700
Data Index: 4467646 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4883. Min Act: -0.1700
Data Index: 1236467 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4558. Min Act: -0.1700
Data Index: 7799323 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4558. Min Act: -0.1700
Data Index: 920160 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4558. Min Act: -0.1700
Data Index: 2120513 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4396. Min Act: -0.1700
Data Index: 2006710 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6335. Min Range: -2.6335
Max Act: 2.4396. Min Act: -0.1700
Data Index: 8024207 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19