Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2042 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3765. Min Range: -7.3765
Max Act: 7.3765. Min Act: -0.1700
Data Index: 8358825 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3765. Min Range: -7.3765
Max Act: 7.1265. Min Act: -0.1700
Data Index: 7985473 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3765. Min Range: -7.3765
Max Act: 7.0952. Min Act: -0.1700
Data Index: 3990051 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3765. Min Range: -7.3765
Max Act: 7.1265. Min Act: -0.1700
Data Index: 5796647 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3765. Min Range: -7.3765
Max Act: 7.0015. Min Act: -0.1700
Data Index: 4213059 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9702. Min Act: -0.1700
Data Index: 7392230 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3765. Min Range: -7.3765
Max Act: 7.0015. Min Act: -0.1700
Data Index: 1118728 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9702. Min Act: -0.1700
Data Index: 3653618 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9390. Min Act: -0.1700
Data Index: 6226389 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9390. Min Act: -0.1700
Data Index: 4206386 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9390. Min Act: -0.1700
Data Index: 3219116 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9077. Min Act: -0.1700
Data Index: 2623612 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9077. Min Act: -0.1700
Data Index: 8320640 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.9390. Min Act: -0.1700
Data Index: 6508997 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.8452. Min Act: -0.1700
Data Index: 8430540 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.8452. Min Act: -0.1700
Data Index: 2898354 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.8452. Min Act: -0.1700
Data Index: 1343071 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.8452. Min Act: -0.1700
Data Index: 7691289 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.8452. Min Act: -0.1700
Data Index: 5607935 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3765. Min Range: -7.3765
Max Act: 6.8765. Min Act: -0.1700
Data Index: 5652138 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19