Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 657 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4957. Min Act: -0.1700
Data Index: 6315765 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4487. Min Act: -0.1700
Data Index: 5833177 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.4643. Min Act: -0.1700
Data Index: 8784621 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3860. Min Act: -0.1700
Data Index: 1152835 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3860. Min Act: -0.1700
Data Index: 4001310 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3546. Min Act: -0.1700
Data Index: 3304755 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3389. Min Act: -0.1700
Data Index: 3002974 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3389. Min Act: -0.1700
Data Index: 6933952 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3232. Min Act: -0.1700
Data Index: 6495275 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3075. Min Act: -0.1700
Data Index: 5069634 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2918. Min Act: -0.1700
Data Index: 1470496 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.3075. Min Act: -0.1700
Data Index: 590194 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2761. Min Act: -0.1700
Data Index: 6925329 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2761. Min Act: -0.1700
Data Index: 1215880 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2761. Min Act: -0.1700
Data Index: 3138298 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2604. Min Act: -0.1700
Data Index: 6601294 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.1976. Min Act: -0.1700
Data Index: 1153531 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2290. Min Act: -0.1700
Data Index: 2835343 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2133. Min Act: -0.1700
Data Index: 8432462 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4957. Min Range: -3.4957
Max Act: 3.2133. Min Act: -0.1700
Data Index: 2603376 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19