Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.3273. Min Act: -0.1700
Data Index: 1939954 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.3273. Min Act: -0.1700
Data Index: 6809501 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.3273. Min Act: -0.1700
Data Index: 6749244 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.2944. Min Act: -0.1699
Data Index: 1610127 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.2449. Min Act: -0.1700
Data Index: 4861263 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.2284. Min Act: -0.1700
Data Index: 212390 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.2118. Min Act: -0.1700
Data Index: 24542 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1952. Min Act: -0.1700
Data Index: 3415271 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.2118. Min Act: -0.1700
Data Index: 8792554 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1786. Min Act: -0.1700
Data Index: 6270337 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1620. Min Act: -0.1700
Data Index: 4003460 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1620. Min Act: -0.1700
Data Index: 2272936 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1786. Min Act: -0.1700
Data Index: 687314 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1786. Min Act: -0.1700
Data Index: 3491076 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1620. Min Act: -0.1700
Data Index: 6737626 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1620. Min Act: -0.1700
Data Index: 8516604 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1453. Min Act: -0.1700
Data Index: 1117994 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1286. Min Act: -0.1700
Data Index: 8823206 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1453. Min Act: -0.1700
Data Index: 6742043 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3273. Min Range: -2.3273
Max Act: 2.1453. Min Act: -0.1700
Data Index: 4246314 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19