Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.5526. Min Act: -0.1700
Data Index: 8710392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 4739111 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 5022081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 8819535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 2281278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.5213. Min Act: -0.1700
Data Index: 7669794 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.4276. Min Act: -0.1700
Data Index: 1949801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.4276. Min Act: -0.1700
Data Index: 2814946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1696
Data Index: 7598251 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 1835550 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 925770 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 2047446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 6447819 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 6356582 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 8392793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 5786327 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 5546276 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3963. Min Act: -0.1700
Data Index: 1582150 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3651. Min Act: -0.1700
Data Index: 2838820 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5526. Min Range: -4.5526
Max Act: 4.3651. Min Act: -0.1700
Data Index: 272232 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19