Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4960. Min Range: -6.4960
Max Act: 6.4960. Min Act: -0.1700
Data Index: 8672792 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4960. Min Range: -6.4960
Max Act: 6.4022. Min Act: -0.1700
Data Index: 8714145 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 8520625 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 7484610 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 790696 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6641309 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 2805325 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5020046 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 4154538 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 3519126 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6489109 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 4529685 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 3889755 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 2293928 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 7001073 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 250609 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6522. Min Act: -0.1700
Data Index: 7570802 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6210. Min Act: -0.1700
Data Index: 6855188 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6522. Min Act: -0.1700
Data Index: 7494627 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4960. Min Range: -6.4960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 7041680 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19