Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3818. Min Act: -0.1700
Data Index: 3545964 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 2826528 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 1835804 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2255. Min Act: -0.1700
Data Index: 2249031 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2255. Min Act: -0.1700
Data Index: 4710128 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1943. Min Act: -0.1700
Data Index: 7423278 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1318. Min Act: -0.1700
Data Index: 5859646 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1318. Min Act: -0.1700
Data Index: 7103594 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1318. Min Act: -0.1700
Data Index: 6917273 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1005. Min Act: -0.1700
Data Index: 2980200 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1005. Min Act: -0.1700
Data Index: 2314424 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1005. Min Act: -0.1700
Data Index: 3098042 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.1005. Min Act: -0.1700
Data Index: 1855929 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 7153962 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 4003481 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 2291373 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 7551914 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 2488287 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 1201959 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.0693. Min Act: -0.1700
Data Index: 7557979 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19