Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.4450. Min Act: -0.1700
Data Index: 5879249 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.4137. Min Act: -0.1700
Data Index: 7561458 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.4137. Min Act: -0.1700
Data Index: 2246947 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.4137. Min Act: -0.1700
Data Index: 3590480 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3667. Min Act: -0.1700
Data Index: 1098821 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3510. Min Act: -0.1700
Data Index: 2433090 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3353. Min Act: -0.1700
Data Index: 258339 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3353. Min Act: -0.1700
Data Index: 469931 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3196. Min Act: -0.1700
Data Index: 6076295 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 7599522 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 7532834 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 1317798 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 4339031 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 4008613 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 7417207 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.3039. Min Act: -0.1700
Data Index: 2336567 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.2882. Min Act: -0.1700
Data Index: 2460246 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.2882. Min Act: -0.1700
Data Index: 4912654 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.2882. Min Act: -0.1700
Data Index: 5857035 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4450. Min Range: -3.4450
Max Act: 3.2882. Min Act: -0.1700
Data Index: 3983359 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19