Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3726 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.1258. Min Act: -0.1700
Data Index: 6432170 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.0628. Min Act: -0.1700
Data Index: 4340577 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.0628. Min Act: -0.1700
Data Index: 120161 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.0470. Min Act: -0.1700
Data Index: 2640673 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.0312. Min Act: -0.1700
Data Index: 2328111 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.0154. Min Act: -0.1700
Data Index: 3210965 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9522. Min Act: -0.1700
Data Index: 1721760 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9522. Min Act: -0.1700
Data Index: 2908740 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9363. Min Act: -0.1700
Data Index: 1523811 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9363. Min Act: -0.1700
Data Index: 9352 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9522. Min Act: -0.1700
Data Index: 7052397 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9363. Min Act: -0.1700
Data Index: 8038818 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9205. Min Act: -0.1700
Data Index: 5870712 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9205. Min Act: -0.1700
Data Index: 6923043 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8888. Min Act: -0.1700
Data Index: 1335329 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9046. Min Act: -0.1700
Data Index: 4715292 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9046. Min Act: -0.1700
Data Index: 8350803 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9205. Min Act: -0.1700
Data Index: 5274948 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9046. Min Act: -0.1700
Data Index: 8776290 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9046. Min Act: -0.1700
Data Index: 8033050 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19