Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.2092. Min Act: -0.1700
Data Index: 5519384 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1934. Min Act: -0.1700
Data Index: 3827263 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1777. Min Act: -0.1700
Data Index: 7671346 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1462. Min Act: -0.1700
Data Index: 3528537 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.1147. Min Act: -0.1700
Data Index: 5350519 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0675. Min Act: -0.1700
Data Index: 7198025 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0675. Min Act: -0.1700
Data Index: 1792251 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0359. Min Act: -0.1700
Data Index: 5554550 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2092. Min Range: -3.2092
Max Act: 3.0201. Min Act: -0.1700
Data Index: 5519383 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9885. Min Act: -0.1700
Data Index: 5502158 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9885. Min Act: -0.1700
Data Index: 5350520 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9569. Min Act: -0.1700
Data Index: 3351802 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9569. Min Act: -0.1700
Data Index: 2434235 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9252. Min Act: -0.1700
Data Index: 2865033 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9093. Min Act: -0.1700
Data Index: 1065185 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9093. Min Act: -0.1700
Data Index: 5350524 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.8776. Min Act: -0.1700
Data Index: 1798873 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.8935. Min Act: -0.1700
Data Index: 5350521 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.9252. Min Act: -0.1700
Data Index: 2735156 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2092. Min Range: -3.2092
Max Act: 2.8776. Min Act: -0.1700
Data Index: 5493318 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19